Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3955. Min Range: -6.3955
Max Act: 6.3955. Min Act: -0.1700
Data Index: 6670768 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.8017. Min Act: -0.1700
Data Index: 2606965 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.7705. Min Act: -0.1700
Data Index: 5708931 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.6767. Min Act: -0.1700
Data Index: 2731121 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.5830. Min Act: -0.1700
Data Index: 567173 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.5517. Min Act: -0.1700
Data Index: 3734456 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.5517. Min Act: -0.1700
Data Index: 3149108 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.5205. Min Act: -0.1700
Data Index: 6705214 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.5205. Min Act: -0.1700
Data Index: 6437156 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.5205. Min Act: -0.1700
Data Index: 643626 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4892. Min Act: -0.1700
Data Index: 3475864 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4580. Min Act: -0.1700
Data Index: 7652119 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4580. Min Act: -0.1700
Data Index: 245771 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4580. Min Act: -0.1700
Data Index: 2217390 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4580. Min Act: -0.1700
Data Index: 3321052 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4892. Min Act: -0.1700
Data Index: 687739 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4580. Min Act: -0.1700
Data Index: 1143540 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4580. Min Act: -0.1700
Data Index: 2004574 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4267. Min Act: -0.1700
Data Index: 5563870 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3955. Min Range: -6.3955
Max Act: 5.4267. Min Act: -0.1700
Data Index: 1616604 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19