Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1964 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.6367. Min Act: -0.1700
Data Index: 8258645 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.6055. Min Act: -0.1700
Data Index: 8258644 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.5117. Min Act: -0.1700
Data Index: 7486 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.5117. Min Act: -0.1700
Data Index: 8258643 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.4492. Min Act: -0.1700
Data Index: 3092028 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.4492. Min Act: -0.1700
Data Index: 1902716 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3867. Min Act: -0.1700
Data Index: 514847 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.4180. Min Act: -0.1700
Data Index: 3067881 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3867. Min Act: -0.1700
Data Index: 3937838 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3867. Min Act: -0.1700
Data Index: 1445087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3867. Min Act: -0.1700
Data Index: 8541734 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 7282944 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3555. Min Act: -0.1700
Data Index: 590348 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 3873891 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 3183760 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 5722134 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 2315558 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 1627336 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3555. Min Act: -0.1700
Data Index: 8461490 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6367. Min Range: -4.6367
Max Act: 4.3242. Min Act: -0.1700
Data Index: 7105005 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19