Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1281 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.4128. Min Act: -0.1700
Data Index: 1447101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3503. Min Act: -0.1700
Data Index: 7899770 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3191. Min Act: -0.1700
Data Index: 6075985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.3191. Min Act: -0.1700
Data Index: 4764916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2878. Min Act: -0.1700
Data Index: 1929019 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2566. Min Act: -0.1700
Data Index: 1604328 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2878. Min Act: -0.1700
Data Index: 6166404 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2878. Min Act: -0.1700
Data Index: 7888171 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2566. Min Act: -0.1700
Data Index: 6708840 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2566. Min Act: -0.1700
Data Index: 5428329 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 3062648 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 5802760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 6865622 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 1411239 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 5166327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 510355 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1941. Min Act: -0.1700
Data Index: 4099530 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.2253. Min Act: -0.1700
Data Index: 1111892 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1941. Min Act: -0.1700
Data Index: 6533456 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4128. Min Range: -5.4128
Max Act: 5.1941. Min Act: -0.1700
Data Index: 4094515 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19