Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1030 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2917. Min Range: -6.2917
Max Act: 6.2917. Min Act: -0.1700
Data Index: 4409406 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2917. Min Range: -6.2917
Max Act: 6.2917. Min Act: -0.1700
Data Index: 8642999 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2917. Min Range: -6.2917
Max Act: 6.1042. Min Act: -0.1700
Data Index: 1488930 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2917. Min Range: -6.2917
Max Act: 6.0417. Min Act: -0.1700
Data Index: 883579 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.9792. Min Act: -0.1700
Data Index: 1960369 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.9479. Min Act: -0.1700
Data Index: 2294817 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.9479. Min Act: -0.1700
Data Index: 1728133 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.9792. Min Act: -0.1700
Data Index: 1577621 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.9479. Min Act: -0.1700
Data Index: 805655 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.9479. Min Act: -0.1700
Data Index: 2842171 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8854. Min Act: -0.1700
Data Index: 5659062 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8542. Min Act: -0.1700
Data Index: 4522375 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8542. Min Act: -0.1700
Data Index: 6942987 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8229. Min Act: -0.1700
Data Index: 477979 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8854. Min Act: -0.1700
Data Index: 425831 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8542. Min Act: -0.1700
Data Index: 8692420 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.7917. Min Act: -0.1700
Data Index: 4738150 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.8542. Min Act: -0.1700
Data Index: 3362108 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.7292. Min Act: -0.1700
Data Index: 5862461 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2917. Min Range: -6.2917
Max Act: 5.7917. Min Act: -0.1700
Data Index: 8162624 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19