Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3198. Min Range: -7.3198
Max Act: 7.3198. Min Act: -0.1700
Data Index: 3737246 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3198. Min Range: -7.3198
Max Act: 7.1948. Min Act: -0.1700
Data Index: 6702809 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3198. Min Range: -7.3198
Max Act: 7.1635. Min Act: -0.1700
Data Index: 2709579 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3198. Min Range: -7.3198
Max Act: 7.1010. Min Act: -0.1700
Data Index: 130776 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.9760. Min Act: -0.1700
Data Index: 4343668 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.9760. Min Act: -0.1700
Data Index: 955394 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.9135. Min Act: -0.1700
Data Index: 4692073 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.8510. Min Act: -0.1700
Data Index: 8499271 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7885. Min Act: -0.1700
Data Index: 5413468 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7885. Min Act: -0.1700
Data Index: 5224786 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7885. Min Act: -0.1700
Data Index: 5704130 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7573. Min Act: -0.1700
Data Index: 7348400 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7260. Min Act: -0.1700
Data Index: 5796760 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7260. Min Act: -0.1700
Data Index: 3892618 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.7260. Min Act: -0.1700
Data Index: 4072587 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.6948. Min Act: -0.1700
Data Index: 242252 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.6635. Min Act: -0.1700
Data Index: 3882797 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.6635. Min Act: -0.1700
Data Index: 4266656 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.6635. Min Act: -0.1700
Data Index: 4750130 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3198. Min Range: -7.3198
Max Act: 6.6010. Min Act: -0.1700
Data Index: 1904014 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19