Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4520 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.6968. Min Act: -0.1700
Data Index: 2505754 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.6031. Min Act: -0.1700
Data Index: 7755687 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.6343. Min Act: -0.1700
Data Index: 7545206 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.4468. Min Act: -0.1700
Data Index: 445799 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.3843. Min Act: -0.1700
Data Index: 7801709 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.3218. Min Act: -0.1700
Data Index: 1980212 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.3218. Min Act: -0.1700
Data Index: 8034601 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.2906. Min Act: -0.1700
Data Index: 3524828 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.2906. Min Act: -0.1700
Data Index: 4335724 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.2593. Min Act: -0.1700
Data Index: 5070075 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.2593. Min Act: -0.1700
Data Index: 8243144 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1968. Min Act: -0.1700
Data Index: 7755793 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1968. Min Act: -0.1700
Data Index: 4128711 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1343. Min Act: -0.1700
Data Index: 4741633 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1343. Min Act: -0.1700
Data Index: 7332587 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1343. Min Act: -0.1700
Data Index: 6150089 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1031. Min Act: -0.1700
Data Index: 5795527 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1656. Min Act: -0.1700
Data Index: 5727786 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1031. Min Act: -0.1700
Data Index: 5231247 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6968. Min Range: -6.6968
Max Act: 6.1031. Min Act: -0.1700
Data Index: 1818552 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19