Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 712 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.4698. Min Act: -0.1700
Data Index: 5815831 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.3760. Min Act: -0.1700
Data Index: 6614008 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.3448. Min Act: -0.1700
Data Index: 8134110 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.3135. Min Act: -0.1700
Data Index: 1339869 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2510. Min Act: -0.1700
Data Index: 5623258 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2510. Min Act: -0.1700
Data Index: 5359417 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2510. Min Act: -0.1700
Data Index: 7468359 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2198. Min Act: -0.1700
Data Index: 1408229 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2510. Min Act: -0.1700
Data Index: 5226953 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2198. Min Act: -0.1700
Data Index: 3179426 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1885. Min Act: -0.1700
Data Index: 6287165 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1885. Min Act: -0.1700
Data Index: 3281446 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.2198. Min Act: -0.1700
Data Index: 4352679 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1885. Min Act: -0.1700
Data Index: 4772928 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1885. Min Act: -0.1700
Data Index: 3167458 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1573. Min Act: -0.1700
Data Index: 6435422 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1573. Min Act: -0.1700
Data Index: 1453931 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1573. Min Act: -0.1700
Data Index: 2112025 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1573. Min Act: -0.1700
Data Index: 4518868 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4698. Min Range: -5.4698
Max Act: 5.1573. Min Act: -0.1700
Data Index: 4117485 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19