Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4273 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.7918. Min Act: -0.1700
Data Index: 3837069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.5418. Min Act: -0.1700
Data Index: 2871631 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.5418. Min Act: -0.1700
Data Index: 8177583 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 3975443 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 8823282 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 3551122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 3477552 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 2652459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 1459333 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 5250415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 4973295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 7671959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 6537296 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 2779037 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4793. Min Act: -0.1700
Data Index: 6426798 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4481. Min Act: -0.1700
Data Index: 2450844 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4481. Min Act: -0.1700
Data Index: 4255656 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4168. Min Act: -0.1700
Data Index: 7843791 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4168. Min Act: -0.1700
Data Index: 4059455 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7918. Min Range: -6.7918
Max Act: 6.4168. Min Act: -0.1700
Data Index: 3147755 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19