Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.8490. Min Act: -0.1700
Data Index: 8225671 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.8802. Min Act: -0.1700
Data Index: 212465 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.8802. Min Act: -0.1700
Data Index: 873394 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.7865. Min Act: -0.1700
Data Index: 3068063 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.7240. Min Act: -0.1700
Data Index: 1044958 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 6683547 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.7240. Min Act: -0.1699
Data Index: 3170276 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.7240. Min Act: -0.1700
Data Index: 8745246 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 4769328 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 4539512 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.7240. Min Act: -0.1700
Data Index: 8706435 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 7016897 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6927. Min Act: -0.1700
Data Index: 5852115 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 4318282 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 6116637 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 6273429 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 4450993 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 2178049 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 6547674 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8802. Min Range: -5.8802
Max Act: 5.6615. Min Act: -0.1700
Data Index: 516612 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19