Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.6268. Min Act: -0.1700
Data Index: 3321872 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.5643. Min Act: -0.1700
Data Index: 7428698 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.3455. Min Act: -0.1700
Data Index: 1243422 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.2518. Min Act: -0.1700
Data Index: 4237154 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.1893. Min Act: -0.1700
Data Index: 6166890 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.1580. Min Act: -0.1700
Data Index: 6543729 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0955. Min Act: -0.1700
Data Index: 6496416 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 577091 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 4206411 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 6211270 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 2815371 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 7091846 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0330. Min Act: -0.1700
Data Index: 5440214 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 7045356 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0955. Min Act: -0.1700
Data Index: 3238578 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0018. Min Act: -0.1700
Data Index: 27547 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0330. Min Act: -0.1700
Data Index: 2701342 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0330. Min Act: -0.1700
Data Index: 4851090 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0643. Min Act: -0.1700
Data Index: 6608789 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6268. Min Range: -7.6268
Max Act: 7.0018. Min Act: -0.1700
Data Index: 4927089 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19