Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6127 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.0115. Min Range: -15.0115
Max Act: 15.0115. Min Act: -0.1700
Data Index: 8200017 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.6990. Min Act: -0.1700
Data Index: 3587895 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.5740. Min Act: -0.1700
Data Index: 5509425 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.4490. Min Act: -0.1700
Data Index: 5743192 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.4490. Min Act: -0.1700
Data Index: 1886911 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.4490. Min Act: -0.1700
Data Index: 1302502 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.3865. Min Act: -0.1700
Data Index: 8457086 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.2615. Min Act: -0.1700
Data Index: 345694 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.3240. Min Act: -0.1700
Data Index: 1218236 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.2615. Min Act: -0.1700
Data Index: 4400211 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.2615. Min Act: -0.1700
Data Index: 3729281 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.1990. Min Act: -0.1700
Data Index: 676669 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.2615. Min Act: -0.1700
Data Index: 6327136 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.2615. Min Act: -0.1700
Data Index: 8240114 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.1990. Min Act: -0.1700
Data Index: 3206814 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.1365. Min Act: -0.1700
Data Index: 326832 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.1365. Min Act: -0.1700
Data Index: 1776159 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.1365. Min Act: -0.1700
Data Index: 7030678 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.0740. Min Act: -0.1700
Data Index: 7286866 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.0115. Min Range: -15.0115
Max Act: 14.1365. Min Act: -0.1700
Data Index: 7549320 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19