Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.7402. Min Act: -0.1700
Data Index: 7553769 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.6150. Min Act: -0.1700
Data Index: 171895 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.6307. Min Act: -0.1700
Data Index: 7852721 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.5211. Min Act: -0.1700
Data Index: 709375 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4898. Min Act: -0.1700
Data Index: 8059006 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.5055. Min Act: -0.1700
Data Index: 4744782 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4741. Min Act: -0.1700
Data Index: 8727016 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4585. Min Act: -0.1700
Data Index: 76080 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4741. Min Act: -0.1700
Data Index: 3775314 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4585. Min Act: -0.1700
Data Index: 4865926 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4585. Min Act: -0.1700
Data Index: 2040868 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4428. Min Act: -0.1700
Data Index: 679743 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4271. Min Act: -0.1700
Data Index: 4421329 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4428. Min Act: -0.1700
Data Index: 4008665 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4271. Min Act: -0.1700
Data Index: 8191914 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 907138 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4271. Min Act: -0.1700
Data Index: 3796720 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 8533105 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4271. Min Act: -0.1700
Data Index: 277461 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 601490 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19