Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.7608. Min Act: -0.1700
Data Index: 2536584 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.7139. Min Act: -0.1700
Data Index: 5196571 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.6356. Min Act: -0.1700
Data Index: 3665309 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5887. Min Act: -0.1700
Data Index: 7394592 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5887. Min Act: -0.1700
Data Index: 1563429 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5887. Min Act: -0.1700
Data Index: 3147202 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5887. Min Act: -0.1700
Data Index: 5272917 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5730. Min Act: -0.1700
Data Index: 1956822 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5417. Min Act: -0.1700
Data Index: 6804353 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5574. Min Act: -0.1700
Data Index: 3369013 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5261. Min Act: -0.1700
Data Index: 3774096 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5104. Min Act: -0.1700
Data Index: 2582063 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5261. Min Act: -0.1700
Data Index: 2216281 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5261. Min Act: -0.1700
Data Index: 6406868 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.4947. Min Act: -0.1700
Data Index: 8252976 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.5261. Min Act: -0.1700
Data Index: 7608433 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.4947. Min Act: -0.1700
Data Index: 1956823 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.4947. Min Act: -0.1700
Data Index: 4353887 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.4947. Min Act: -0.1700
Data Index: 7058825 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7608. Min Range: -3.7608
Max Act: 3.4947. Min Act: -0.1700
Data Index: 7182411 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19