Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1268. Min Range: -7.1268
Max Act: 7.1268. Min Act: -0.1700
Data Index: 7391496 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.8143. Min Act: -0.1700
Data Index: 300982 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.8455. Min Act: -0.1700
Data Index: 632943 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.8143. Min Act: -0.1700
Data Index: 5751963 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.7205. Min Act: -0.1700
Data Index: 221631 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.7518. Min Act: -0.1700
Data Index: 1907847 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.7518. Min Act: -0.1700
Data Index: 7498599 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.7518. Min Act: -0.1700
Data Index: 5893211 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6893. Min Act: -0.1700
Data Index: 3164922 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6893. Min Act: -0.1700
Data Index: 1400660 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6893. Min Act: -0.1700
Data Index: 3164028 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6893. Min Act: -0.1700
Data Index: 3403793 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6580. Min Act: -0.1700
Data Index: 5640126 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6580. Min Act: -0.1699
Data Index: 2389681 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6580. Min Act: -0.1700
Data Index: 5612868 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6893. Min Act: -0.1700
Data Index: 1011094 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6580. Min Act: -0.1698
Data Index: 5543754 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6580. Min Act: -0.1700
Data Index: 1936830 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.6268. Min Act: -0.1700
Data Index: 901957 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1268. Min Range: -7.1268
Max Act: 6.5955. Min Act: -0.1700
Data Index: 2887715 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19