Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1082. Min Range: -6.1082
Max Act: 6.1082. Min Act: -0.1700
Data Index: 6217167 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.9832. Min Act: -0.1700
Data Index: 8568622 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.9207. Min Act: -0.1700
Data Index: 4472481 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.8582. Min Act: -0.1700
Data Index: 1203075 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7644. Min Act: -0.1700
Data Index: 168031 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7332. Min Act: -0.1700
Data Index: 6999014 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.6707. Min Act: -0.1700
Data Index: 5420765 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.6707. Min Act: -0.1700
Data Index: 3200073 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.6707. Min Act: -0.1700
Data Index: 1769055 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6964233 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5457. Min Act: -0.1700
Data Index: 7378504 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5457. Min Act: -0.1700
Data Index: 8127241 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5144. Min Act: -0.1700
Data Index: 2861005 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5144. Min Act: -0.1700
Data Index: 959762 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4832. Min Act: -0.1700
Data Index: 3238763 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 4468300 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4832. Min Act: -0.1700
Data Index: 684183 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 3780467 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2209828 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 7135344 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19