Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.2820. Min Act: -0.1700
Data Index: 977541 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0945. Min Act: -0.1700
Data Index: 702584 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0633. Min Act: -0.1700
Data Index: 2872708 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2820. Min Range: -5.2820
Max Act: 5.0633. Min Act: -0.1700
Data Index: 3277720 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.9383. Min Act: -0.1700
Data Index: 1173956 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.9070. Min Act: -0.1700
Data Index: 7037289 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.8758. Min Act: -0.1700
Data Index: 8259626 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.8758. Min Act: -0.1700
Data Index: 673708 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.8133. Min Act: -0.1700
Data Index: 979787 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.7820. Min Act: -0.1700
Data Index: 2166210 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.7195. Min Act: -0.1700
Data Index: 4909728 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.7195. Min Act: -0.1700
Data Index: 323339 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.7195. Min Act: -0.1700
Data Index: 7370187 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.7195. Min Act: -0.1700
Data Index: 3957280 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.6883. Min Act: -0.1700
Data Index: 7080910 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.6883. Min Act: -0.1700
Data Index: 7600411 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.6570. Min Act: -0.1700
Data Index: 8594589 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.6570. Min Act: -0.1700
Data Index: 765401 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.6570. Min Act: -0.1700
Data Index: 6234630 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2820. Min Range: -5.2820
Max Act: 4.6258. Min Act: -0.1700
Data Index: 8493912 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19