Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3523 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2021. Min Range: -8.2021
Max Act: 8.2021. Min Act: -0.1700
Data Index: 6418016 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.9209. Min Act: -0.1700
Data Index: 4439143 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.9209. Min Act: -0.1700
Data Index: 3224536 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.8271. Min Act: -0.1700
Data Index: 5001685 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.7646. Min Act: -0.1700
Data Index: 3607128 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.6709. Min Act: -0.1700
Data Index: 8138196 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.6396. Min Act: -0.1700
Data Index: 805754 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.6084. Min Act: -0.1700
Data Index: 5509715 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.5771. Min Act: -0.1700
Data Index: 5505553 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.4834. Min Act: -0.1700
Data Index: 8447970 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.4521. Min Act: -0.1700
Data Index: 4872642 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.4521. Min Act: -0.1700
Data Index: 3552682 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.4521. Min Act: -0.1700
Data Index: 1346307 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.4209. Min Act: -0.1700
Data Index: 3076023 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.4521. Min Act: -0.1700
Data Index: 2390455 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.3896. Min Act: -0.1700
Data Index: 2444423 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.3584. Min Act: -0.1700
Data Index: 6948738 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.3896. Min Act: -0.1700
Data Index: 2725727 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.2646. Min Act: -0.1700
Data Index: 1042210 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2021. Min Range: -8.2021
Max Act: 7.2646. Min Act: -0.1700
Data Index: 130026 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19