Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.9113. Min Act: -0.1700
Data Index: 44794 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.8488. Min Act: -0.1700
Data Index: 7666119 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.8175. Min Act: -0.1700
Data Index: 7775235 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.7863. Min Act: -0.1700
Data Index: 8342623 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6613. Min Act: -0.1700
Data Index: 8179331 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6613. Min Act: -0.1700
Data Index: 6823811 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6300. Min Act: -0.1700
Data Index: 437102 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6300. Min Act: -0.1700
Data Index: 5457393 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.6613. Min Act: -0.1700
Data Index: 1617461 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5988. Min Act: -0.1700
Data Index: 6854902 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 124081 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5675. Min Act: -0.1700
Data Index: 3800690 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5675. Min Act: -0.1700
Data Index: 18913 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 7721331 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 1526347 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5050. Min Act: -0.1700
Data Index: 4011755 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5363. Min Act: -0.1700
Data Index: 1617459 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5050. Min Act: -0.1700
Data Index: 6214524 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.5050. Min Act: -0.1700
Data Index: 1413772 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9113. Min Range: -4.9113
Max Act: 4.4737. Min Act: -0.1700
Data Index: 6966713 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19