Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 446 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1823. Min Range: -7.1823
Max Act: 7.1823. Min Act: -0.1700
Data Index: 3203116 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1823. Min Range: -7.1823
Max Act: 7.1198. Min Act: -0.1700
Data Index: 3863271 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1823. Min Range: -7.1823
Max Act: 7.0573. Min Act: -0.1700
Data Index: 42913 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1823. Min Range: -7.1823
Max Act: 7.0261. Min Act: -0.1700
Data Index: 1519592 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9948. Min Act: -0.1700
Data Index: 3098902 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1823. Min Range: -7.1823
Max Act: 7.0261. Min Act: -0.1700
Data Index: 2656078 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9323. Min Act: -0.1700
Data Index: 1578862 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9323. Min Act: -0.1700
Data Index: 2655074 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9323. Min Act: -0.1700
Data Index: 75695 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9011. Min Act: -0.1700
Data Index: 7599769 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9011. Min Act: -0.1700
Data Index: 5786923 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8698. Min Act: -0.1700
Data Index: 8094753 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.9011. Min Act: -0.1700
Data Index: 3086585 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8386. Min Act: -0.1700
Data Index: 8050328 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8698. Min Act: -0.1700
Data Index: 4745935 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8073. Min Act: -0.1700
Data Index: 5831215 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8386. Min Act: -0.1700
Data Index: 6012161 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8073. Min Act: -0.1700
Data Index: 8373203 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8386. Min Act: -0.1700
Data Index: 7542674 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1823. Min Range: -7.1823
Max Act: 6.8386. Min Act: -0.1700
Data Index: 2357666 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19