Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5339 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.4771. Min Act: -0.1700
Data Index: 8650817 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.3521. Min Act: -0.1700
Data Index: 1883707 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.2896. Min Act: -0.1700
Data Index: 952576 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.2896. Min Act: -0.1700
Data Index: 5424851 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.2271. Min Act: -0.1700
Data Index: 8341380 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.2271. Min Act: -0.1700
Data Index: 2012922 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1646. Min Act: -0.1700
Data Index: 6384546 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1334. Min Act: -0.1700
Data Index: 3287145 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1334. Min Act: -0.1700
Data Index: 7036782 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1021. Min Act: -0.1700
Data Index: 5105135 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1021. Min Act: -0.1700
Data Index: 784452 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1021. Min Act: -0.1700
Data Index: 4328973 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.1021. Min Act: -0.1700
Data Index: 5607089 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0709. Min Act: -0.1700
Data Index: 3312553 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0709. Min Act: -0.1700
Data Index: 4612510 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0709. Min Act: -0.1700
Data Index: 846353 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0709. Min Act: -0.1700
Data Index: 4740293 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4448026 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4145907 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4771. Min Range: -5.4771
Max Act: 5.0396. Min Act: -0.1700
Data Index: 6497566 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19