Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1317 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.9240. Min Act: -0.1700
Data Index: 6427694 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.7990. Min Act: -0.1700
Data Index: 2140312 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.6740. Min Act: -0.1700
Data Index: 2799531 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.5177. Min Act: -0.1700
Data Index: 1630042 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.5490. Min Act: -0.1700
Data Index: 4903367 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.5490. Min Act: -0.1700
Data Index: 6947036 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.4865. Min Act: -0.1700
Data Index: 5873026 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.4240. Min Act: -0.1700
Data Index: 2450573 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.4240. Min Act: -0.1700
Data Index: 5247355 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3927. Min Act: -0.1700
Data Index: 6880617 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3927. Min Act: -0.1700
Data Index: 7302005 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3927. Min Act: -0.1700
Data Index: 7400892 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3927. Min Act: -0.1700
Data Index: 3430529 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3927. Min Act: -0.1700
Data Index: 6186299 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3615. Min Act: -0.1700
Data Index: 371690 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3302. Min Act: -0.1700
Data Index: 506382 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.2990. Min Act: -0.1700
Data Index: 3918849 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3615. Min Act: -0.1700
Data Index: 8097191 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.3302. Min Act: -0.1700
Data Index: 8129045 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9240. Min Range: -7.9240
Max Act: 7.2990. Min Act: -0.1700
Data Index: 4920620 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19