Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1695. Min Range: -5.1695
Max Act: 5.1695. Min Act: -0.1700
Data Index: 8455988 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1695. Min Range: -5.1695
Max Act: 5.0445. Min Act: -0.1700
Data Index: 5911156 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9820. Min Act: -0.1700
Data Index: 5198657 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9820. Min Act: -0.1700
Data Index: 3975916 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9820. Min Act: -0.1700
Data Index: 2888879 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9820. Min Act: -0.1700
Data Index: 121339 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9507. Min Act: -0.1700
Data Index: 6108519 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9195. Min Act: -0.1700
Data Index: 8517877 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9820. Min Act: -0.1700
Data Index: 5785007 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9195. Min Act: -0.1700
Data Index: 2304164 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9507. Min Act: -0.1700
Data Index: 593469 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9195. Min Act: -0.1700
Data Index: 1395494 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.8882. Min Act: -0.1700
Data Index: 2483916 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9195. Min Act: -0.1700
Data Index: 1451608 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9195. Min Act: -0.1700
Data Index: 3524954 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.9195. Min Act: -0.1700
Data Index: 7767347 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.8882. Min Act: -0.1700
Data Index: 810396 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.8882. Min Act: -0.1700
Data Index: 2930272 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.8882. Min Act: -0.1700
Data Index: 548461 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1695. Min Range: -5.1695
Max Act: 4.8570. Min Act: -0.1700
Data Index: 4455903 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19