Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 932 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.6262. Min Act: -0.1700
Data Index: 2204215 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.6262. Min Act: -0.1700
Data Index: 108770 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.6262. Min Act: -0.1700
Data Index: 8415603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.6262. Min Act: -0.1700
Data Index: 6605374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5949. Min Act: -0.1700
Data Index: 6126683 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5636. Min Act: -0.1700
Data Index: 3542544 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 2317279 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 6138571 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 3626663 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 6981993 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 7198624 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 7249514 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 4417762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 3298869 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5322. Min Act: -0.1700
Data Index: 5370925 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5009. Min Act: -0.1700
Data Index: 642980 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5009. Min Act: -0.1700
Data Index: 5167151 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5009. Min Act: -0.1700
Data Index: 1875527 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5009. Min Act: -0.1700
Data Index: 3274192 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6262. Min Range: -3.6262
Max Act: 3.5009. Min Act: -0.1700
Data Index: 5263946 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19