Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.6152. Min Act: -0.1700
Data Index: 7733252 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.4902. Min Act: -0.1700
Data Index: 2588531 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.4589. Min Act: -0.1700
Data Index: 1861263 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.4589. Min Act: -0.1700
Data Index: 149562 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.3339. Min Act: -0.1700
Data Index: 4972851 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.3339. Min Act: -0.1700
Data Index: 1763582 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2714. Min Act: -0.1700
Data Index: 5956380 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2714. Min Act: -0.1700
Data Index: 3647296 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2714. Min Act: -0.1700
Data Index: 1021332 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2089. Min Act: -0.1700
Data Index: 7730909 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2402. Min Act: -0.1700
Data Index: 2073140 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2402. Min Act: -0.1700
Data Index: 6983830 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2149235 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2544747 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2588526 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.1777. Min Act: -0.1700
Data Index: 7191456 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.1464. Min Act: -0.1700
Data Index: 7476907 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.1777. Min Act: -0.1700
Data Index: 2775382 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.1777. Min Act: -0.1700
Data Index: 1407403 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6152. Min Range: -4.6152
Max Act: 4.1777. Min Act: -0.1700
Data Index: 6959197 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19