Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5463 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2171. Min Range: -8.2171
Max Act: 8.2171. Min Act: -0.1700
Data Index: 4379822 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2171. Min Range: -8.2171
Max Act: 8.0296. Min Act: -0.1700
Data Index: 2856836 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.9671. Min Act: -0.1700
Data Index: 6691371 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.8108. Min Act: -0.1700
Data Index: 1426816 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.8108. Min Act: -0.1700
Data Index: 4707118 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.7483. Min Act: -0.1700
Data Index: 5691928 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.6858. Min Act: -0.1700
Data Index: 4398192 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.6546. Min Act: -0.1700
Data Index: 4707117 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.6233. Min Act: -0.1700
Data Index: 1836743 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.6233. Min Act: -0.1700
Data Index: 6208305 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5921. Min Act: -0.1700
Data Index: 7564257 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5921. Min Act: -0.1700
Data Index: 624866 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5608. Min Act: -0.1700
Data Index: 6501872 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5608. Min Act: -0.1700
Data Index: 6023447 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5608. Min Act: -0.1700
Data Index: 3866902 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5296. Min Act: -0.1700
Data Index: 7991863 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.5296. Min Act: -0.1700
Data Index: 6862753 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.4983. Min Act: -0.1700
Data Index: 5559499 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.4671. Min Act: -0.1700
Data Index: 4379827 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2171. Min Range: -8.2171
Max Act: 7.4671. Min Act: -0.1700
Data Index: 1312217 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19