Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.4418. Min Act: -0.1700
Data Index: 5767520 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.3480. Min Act: -0.1700
Data Index: 920212 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 5862054 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 5298795 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 8138105 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 6850767 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 8107261 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 7052524 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 4256911 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0980. Min Act: -0.1700
Data Index: 3371939 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 6285925 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.1605. Min Act: -0.1700
Data Index: 908843 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0980. Min Act: -0.1700
Data Index: 7511871 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0980. Min Act: -0.1700
Data Index: 2575105 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0980. Min Act: -0.1700
Data Index: 4725765 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0043. Min Act: -0.1700
Data Index: 5475541 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0355. Min Act: -0.1700
Data Index: 2013554 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0668. Min Act: -0.1700
Data Index: 3097489 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0043. Min Act: -0.1700
Data Index: 1573462 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4418. Min Range: -6.4418
Max Act: 6.0043. Min Act: -0.1700
Data Index: 7232955 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19