Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 231 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.7302. Min Act: -0.1700
Data Index: 6020084 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.7302. Min Act: -0.1700
Data Index: 224808 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.4177. Min Act: -0.1700
Data Index: 3394524 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.2302. Min Act: -0.1700
Data Index: 1146734 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.2302. Min Act: -0.1700
Data Index: 1073545 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.1677. Min Act: -0.1700
Data Index: 7156267 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.1052. Min Act: -0.1700
Data Index: 3599547 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.1052. Min Act: -0.1700
Data Index: 780651 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.0740. Min Act: -0.1700
Data Index: 2736731 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7302. Min Range: -8.7302
Max Act: 8.0427. Min Act: -0.1700
Data Index: 6929371 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.9802. Min Act: -0.1700
Data Index: 3007760 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.9490. Min Act: -0.1700
Data Index: 967057 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.9490. Min Act: -0.1700
Data Index: 6502529 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.7615. Min Act: -0.1700
Data Index: 6065632 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.7615. Min Act: -0.1700
Data Index: 1106672 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.6990. Min Act: -0.1700
Data Index: 8000216 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.6365. Min Act: -0.1700
Data Index: 4509336 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.6365. Min Act: -0.1700
Data Index: 219951 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.6365. Min Act: -0.1700
Data Index: 96786 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7302. Min Range: -8.7302
Max Act: 7.6365. Min Act: -0.1700
Data Index: 4200790 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19