Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.8804. Min Act: -0.1700
Data Index: 3468496 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.8179. Min Act: -0.1700
Data Index: 3357244 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.6304. Min Act: -0.1700
Data Index: 301988 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.5679. Min Act: -0.1700
Data Index: 4559525 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.5054. Min Act: -0.1700
Data Index: 4228975 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.4429. Min Act: -0.1700
Data Index: 3558684 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.3804. Min Act: -0.1700
Data Index: 6501713 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.3804. Min Act: -0.1700
Data Index: 8819674 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.3804. Min Act: -0.1700
Data Index: 1314752 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.2554. Min Act: -0.1700
Data Index: 2839640 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.1929. Min Act: -0.1700
Data Index: 1455397 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.1929. Min Act: -0.1700
Data Index: 44674 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.1304. Min Act: -0.1700
Data Index: 6214636 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.1304. Min Act: -0.1700
Data Index: 3877586 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 2244537 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 700113 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 198145 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 301987 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 4259079 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8804. Min Range: -8.8804
Max Act: 8.0679. Min Act: -0.1700
Data Index: 3957631 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19