Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.9086. Min Act: -0.1700
Data Index: 7082100 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.8461. Min Act: -0.1700
Data Index: 5332771 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.7836. Min Act: -0.1700
Data Index: 2092646 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.7836. Min Act: -0.1700
Data Index: 4881726 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.7836. Min Act: -0.1698
Data Index: 2438340 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.7523. Min Act: -0.1700
Data Index: 7082102 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.7211. Min Act: -0.1700
Data Index: 2001443 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.6898. Min Act: -0.1700
Data Index: 7057888 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.7211. Min Act: -0.1700
Data Index: 4560056 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.6586. Min Act: -0.1700
Data Index: 8362783 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.6586. Min Act: -0.1700
Data Index: 7345422 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.6273. Min Act: -0.1700
Data Index: 7771563 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.6273. Min Act: -0.1700
Data Index: 4886099 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.6273. Min Act: -0.1700
Data Index: 3509141 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.5961. Min Act: -0.1700
Data Index: 6743939 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.5961. Min Act: -0.1700
Data Index: 2246138 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.5648. Min Act: -0.1700
Data Index: 7082101 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.5648. Min Act: -0.1700
Data Index: 7393876 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.5648. Min Act: -0.1700
Data Index: 7639196 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9086. Min Range: -6.9086
Max Act: 6.5648. Min Act: -0.1700
Data Index: 2941706 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19