Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1198 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.5009. Min Act: -0.1700
Data Index: 4416449 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.3284. Min Act: -0.1700
Data Index: 8455715 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2499. Min Act: -0.1700
Data Index: 4738913 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.2028. Min Act: -0.1700
Data Index: 3435945 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.1871. Min Act: -0.1700
Data Index: 4306465 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.1241. Min Act: -0.1700
Data Index: 7554828 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.1083. Min Act: -0.1700
Data Index: 5632058 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.1556. Min Act: -0.1700
Data Index: 8481441 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.1241. Min Act: -0.1700
Data Index: 6731912 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.1083. Min Act: -0.1700
Data Index: 5907548 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0926. Min Act: -0.1700
Data Index: 5472699 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0926. Min Act: -0.1700
Data Index: 866007 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0926. Min Act: -0.1700
Data Index: 2870649 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0768. Min Act: -0.1700
Data Index: 5748348 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0453. Min Act: -0.1700
Data Index: 4589330 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0453. Min Act: -0.1700
Data Index: 2656938 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0453. Min Act: -0.1700
Data Index: 1105284 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0295. Min Act: -0.1700
Data Index: 3677297 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0295. Min Act: -0.1700
Data Index: 2797709 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5009. Min Range: -3.5009
Max Act: 3.0137. Min Act: -0.1700
Data Index: 4928310 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19