Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 432 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.4105. Min Act: -0.1700
Data Index: 2263469 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.3792. Min Act: -0.1700
Data Index: 5161953 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.2542. Min Act: -0.1700
Data Index: 7827114 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.1917. Min Act: -0.1700
Data Index: 3509357 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.1292. Min Act: -0.1700
Data Index: 5482689 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9730. Min Act: -0.1700
Data Index: 693967 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 3638581 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8792. Min Act: -0.1700
Data Index: 7130758 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8792. Min Act: -0.1700
Data Index: 6934818 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8167. Min Act: -0.1700
Data Index: 2045027 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8167. Min Act: -0.1700
Data Index: 1539606 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8167. Min Act: -0.1700
Data Index: 1487928 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7855. Min Act: -0.1700
Data Index: 1640597 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7855. Min Act: -0.1700
Data Index: 3366575 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7855. Min Act: -0.1700
Data Index: 4653685 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7855. Min Act: -0.1700
Data Index: 7202868 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7542. Min Act: -0.1700
Data Index: 1855333 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7230. Min Act: -0.1700
Data Index: 3716976 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7542. Min Act: -0.1700
Data Index: 1965708 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.7542. Min Act: -0.1700
Data Index: 1110054 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19