Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1903 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.1279. Min Act: -0.1700
Data Index: 5753097 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0441. Min Act: -0.1700
Data Index: 8351618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0272. Min Act: -0.1700
Data Index: 2948494 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0272. Min Act: -0.1700
Data Index: 5039580 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0272. Min Act: -0.1700
Data Index: 3594291 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0441. Min Act: -0.1700
Data Index: 7707686 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0103. Min Act: -0.1700
Data Index: 4000264 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0272. Min Act: -0.1700
Data Index: 2570214 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0272. Min Act: -0.1700
Data Index: 6363713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0103. Min Act: -0.1700
Data Index: 6385062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1279. Min Range: -2.1279
Max Act: 2.0103. Min Act: -0.1700
Data Index: 1104500 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9935. Min Act: -0.1700
Data Index: 7011708 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9765. Min Act: -0.1700
Data Index: 990456 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9935. Min Act: -0.1700
Data Index: 598351 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9765. Min Act: -0.1700
Data Index: 5241857 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9765. Min Act: -0.1700
Data Index: 1581012 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9765. Min Act: -0.1700
Data Index: 8623074 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9596. Min Act: -0.1700
Data Index: 2793665 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9765. Min Act: -0.1700
Data Index: 2835084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1279. Min Range: -2.1279
Max Act: 1.9596. Min Act: -0.1700
Data Index: 7750139 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19