Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8742. Min Range: -9.8742
Max Act: 9.8742. Min Act: -0.1700
Data Index: 39317 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8742. Min Range: -9.8742
Max Act: 9.6867. Min Act: -0.1700
Data Index: 8306522 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8742. Min Range: -9.8742
Max Act: 9.6242. Min Act: -0.1700
Data Index: 7897821 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8742. Min Range: -9.8742
Max Act: 9.4992. Min Act: -0.1700
Data Index: 295011 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8742. Min Range: -9.8742
Max Act: 9.4367. Min Act: -0.1700
Data Index: 6223580 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8742. Min Range: -9.8742
Max Act: 9.3742. Min Act: -0.1700
Data Index: 5862406 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.9367. Min Act: -0.1700
Data Index: 6120214 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.6867. Min Act: -0.1700
Data Index: 252621 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.6867. Min Act: -0.1700
Data Index: 7676886 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.6242. Min Act: -0.1700
Data Index: 1681684 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.5617. Min Act: -0.1700
Data Index: 1177241 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.5617. Min Act: -0.1700
Data Index: 6015971 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.4992. Min Act: -0.1700
Data Index: 2833849 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.4992. Min Act: -0.1700
Data Index: 5610151 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.4367. Min Act: -0.1700
Data Index: 2950322 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.3117. Min Act: -0.1700
Data Index: 2494228 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.3117. Min Act: -0.1700
Data Index: 2663380 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.2492. Min Act: -0.1700
Data Index: 6564103 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.1867. Min Act: -0.1700
Data Index: 4517001 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8742. Min Range: -9.8742
Max Act: 8.1867. Min Act: -0.1700
Data Index: 3392808 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19