Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4258 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.5033. Min Act: -0.1700
Data Index: 2655260 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.4221. Min Act: -0.1700
Data Index: 8315883 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.4221. Min Act: -0.1700
Data Index: 6203938 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.4058. Min Act: -0.1700
Data Index: 8393732 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.4058. Min Act: -0.1700
Data Index: 55004 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.4058. Min Act: -0.1700
Data Index: 4924897 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.4058. Min Act: -0.1700
Data Index: 6203935 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3894. Min Act: -0.1700
Data Index: 5617225 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3731. Min Act: -0.1700
Data Index: 8059034 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3894. Min Act: -0.1700
Data Index: 7907010 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3894. Min Act: -0.1700
Data Index: 4905020 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3894. Min Act: -0.1700
Data Index: 3638446 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3731. Min Act: -0.1700
Data Index: 335695 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3567. Min Act: -0.1700
Data Index: 2975463 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3567. Min Act: -0.1700
Data Index: 2840855 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3567. Min Act: -0.1700
Data Index: 7627802 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3567. Min Act: -0.1700
Data Index: 2836286 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3403. Min Act: -0.1700
Data Index: 5104562 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3403. Min Act: -0.1700
Data Index: 5350403 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5033. Min Range: -2.5033
Max Act: 2.3403. Min Act: -0.1700
Data Index: 1296646 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19