Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.4192. Min Act: -0.1700
Data Index: 5913210 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.3255. Min Act: -0.1700
Data Index: 3330709 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.3255. Min Act: -0.1700
Data Index: 6520560 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.2630. Min Act: -0.1700
Data Index: 3556432 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.2317. Min Act: -0.1700
Data Index: 7356091 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.2005. Min Act: -0.1700
Data Index: 4317743 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.2005. Min Act: -0.1700
Data Index: 7469715 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.1067. Min Act: -0.1700
Data Index: 6851911 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.0755. Min Act: -0.1700
Data Index: 5772659 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.0755. Min Act: -0.1700
Data Index: 3007834 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.0442. Min Act: -0.1700
Data Index: 5646466 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4192. Min Range: -5.4192
Max Act: 5.0130. Min Act: -0.1700
Data Index: 316032 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.9505. Min Act: -0.1700
Data Index: 3913744 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.8880. Min Act: -0.1700
Data Index: 8318671 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.7942. Min Act: -0.1700
Data Index: 4456419 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.7630. Min Act: -0.1700
Data Index: 8474003 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.6692. Min Act: -0.1700
Data Index: 5614963 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.6380. Min Act: -0.1700
Data Index: 5551507 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.6067. Min Act: -0.1700
Data Index: 433418 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4192. Min Range: -5.4192
Max Act: 4.6067. Min Act: -0.1700
Data Index: 2091139 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19