Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1231 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.6413. Min Act: -0.1700
Data Index: 7070146 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.4850. Min Act: -0.1700
Data Index: 4699462 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.4538. Min Act: -0.1700
Data Index: 5318716 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.3913. Min Act: -0.1700
Data Index: 6035923 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.2663. Min Act: -0.1700
Data Index: 5275227 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.2350. Min Act: -0.1700
Data Index: 1377591 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.1725. Min Act: -0.1700
Data Index: 6284127 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.1725. Min Act: -0.1700
Data Index: 3772653 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.1413. Min Act: -0.1700
Data Index: 4952508 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.1100. Min Act: -0.1700
Data Index: 6402633 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.1100. Min Act: -0.1700
Data Index: 188111 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.0475. Min Act: -0.1700
Data Index: 1257050 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5038217 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.0163. Min Act: -0.1700
Data Index: 2052166 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.0163. Min Act: -0.1700
Data Index: 6946148 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6413. Min Range: -5.6413
Max Act: 5.0163. Min Act: -0.1700
Data Index: 3974193 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6413. Min Range: -5.6413
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5413131 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6413. Min Range: -5.6413
Max Act: 4.9850. Min Act: -0.1700
Data Index: 6680569 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6413. Min Range: -5.6413
Max Act: 4.9850. Min Act: -0.1700
Data Index: 5914614 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6413. Min Range: -5.6413
Max Act: 4.9850. Min Act: -0.1700
Data Index: 3574835 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19