Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.6349. Min Act: -0.1700
Data Index: 4148004 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.4786. Min Act: -0.1700
Data Index: 4747710 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.4161. Min Act: -0.1700
Data Index: 2709497 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.4474. Min Act: -0.1700
Data Index: 3688429 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.3536. Min Act: -0.1700
Data Index: 1370183 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.2599. Min Act: -0.1700
Data Index: 4328442 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.1661. Min Act: -0.1700
Data Index: 3887197 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.1974. Min Act: -0.1700
Data Index: 4641954 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.1974. Min Act: -0.1700
Data Index: 2242380 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.1349. Min Act: -0.1700
Data Index: 370485 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.0099. Min Act: -0.1700
Data Index: 5705908 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6349. Min Range: -7.6349
Max Act: 7.0099. Min Act: -0.1700
Data Index: 462400 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.9786. Min Act: -0.1700
Data Index: 381910 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.9474. Min Act: -0.1700
Data Index: 4101917 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.9161. Min Act: -0.1700
Data Index: 3419541 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.9474. Min Act: -0.1700
Data Index: 8814509 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.9161. Min Act: -0.1700
Data Index: 6460143 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.9161. Min Act: -0.1700
Data Index: 655815 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.8849. Min Act: -0.1700
Data Index: 6404566 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6349. Min Range: -7.6349
Max Act: 6.8849. Min Act: -0.1700
Data Index: 5254899 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19