Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.9327. Min Act: -0.1700
Data Index: 7564568 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.8077. Min Act: -0.1700
Data Index: 310616 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.8702. Min Act: -0.1700
Data Index: 4277920 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.8077. Min Act: -0.1700
Data Index: 1180749 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.6827. Min Act: -0.1700
Data Index: 4543500 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.8077. Min Act: -0.1700
Data Index: 5308383 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.6827. Min Act: -0.1700
Data Index: 4125859 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.6827. Min Act: -0.1700
Data Index: 7528760 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.6827. Min Act: -0.1700
Data Index: 4205108 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.6827. Min Act: -0.1700
Data Index: 6353494 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.6202. Min Act: -0.1700
Data Index: 6270159 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.4952. Min Act: -0.1700
Data Index: 5284227 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.5577. Min Act: -0.1700
Data Index: 5298991 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.5577. Min Act: -0.1700
Data Index: 7545116 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.4952. Min Act: -0.1700
Data Index: 5855166 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.4327. Min Act: -0.1700
Data Index: 6258764 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.5577. Min Act: -0.1700
Data Index: 180649 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.5577. Min Act: -0.1700
Data Index: 8031585 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.4952. Min Act: -0.1700
Data Index: 4761980 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9327. Min Range: -11.9327
Max Act: 11.4952. Min Act: -0.1700
Data Index: 4372816 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19