Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 932 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.7566. Min Act: -0.1700
Data Index: 1178296 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.6941. Min Act: -0.1700
Data Index: 5143897 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.6628. Min Act: -0.1700
Data Index: 1634001 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.6003. Min Act: -0.1700
Data Index: 8367293 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5378. Min Act: -0.1700
Data Index: 8367294 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5066. Min Act: -0.1700
Data Index: 2375074 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5066. Min Act: -0.1700
Data Index: 7724728 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4753. Min Act: -0.1700
Data Index: 3656207 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.5066. Min Act: -0.1700
Data Index: 7225652 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4441. Min Act: -0.1700
Data Index: 4264583 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4128. Min Act: -0.1700
Data Index: 5775641 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4441. Min Act: -0.1700
Data Index: 8066526 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6864027 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.4128. Min Act: -0.1700
Data Index: 6231795 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3816. Min Act: -0.1700
Data Index: 4298220 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3816. Min Act: -0.1700
Data Index: 3800469 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3503. Min Act: -0.1700
Data Index: 4408206 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3503. Min Act: -0.1700
Data Index: 1107741 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3503. Min Act: -0.1700
Data Index: 1302609 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7566. Min Range: -6.7566
Max Act: 6.3191. Min Act: -0.1700
Data Index: 2301358 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19