Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8421. Min Range: -8.8421
Max Act: 8.8421. Min Act: -0.1700
Data Index: 4333552 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8421. Min Range: -8.8421
Max Act: 8.4671. Min Act: -0.1700
Data Index: 7051140 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8421. Min Range: -8.8421
Max Act: 8.4046. Min Act: -0.1700
Data Index: 4377671 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8421. Min Range: -8.8421
Max Act: 8.2796. Min Act: -0.1700
Data Index: 7121962 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8421. Min Range: -8.8421
Max Act: 8.0921. Min Act: -0.1700
Data Index: 1561347 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.9046. Min Act: -0.1700
Data Index: 7757761 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.9046. Min Act: -0.1700
Data Index: 3122070 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.8421. Min Act: -0.1700
Data Index: 1736315 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.8421. Min Act: -0.1700
Data Index: 7936669 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.7796. Min Act: -0.1700
Data Index: 5804193 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.7171. Min Act: -0.1700
Data Index: 3656381 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.6546. Min Act: -0.1700
Data Index: 1321484 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.6546. Min Act: -0.1700
Data Index: 4870772 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.5921. Min Act: -0.1700
Data Index: 8181994 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.5608. Min Act: -0.1700
Data Index: 2461716 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.5608. Min Act: -0.1700
Data Index: 1898326 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.5608. Min Act: -0.1700
Data Index: 3529249 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.5296. Min Act: -0.1700
Data Index: 7055522 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.4983. Min Act: -0.1700
Data Index: 6708703 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8421. Min Range: -8.8421
Max Act: 7.4983. Min Act: -0.1700
Data Index: 6290466 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19