Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5610 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.8515. Min Act: -0.1700
Data Index: 1972132 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.7890. Min Act: -0.1700
Data Index: 1787190 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.6328. Min Act: -0.1700
Data Index: 2969135 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.5078. Min Act: -0.1700
Data Index: 4698862 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.4765. Min Act: -0.1700
Data Index: 8035989 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.4765. Min Act: -0.1700
Data Index: 272723 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.4453. Min Act: -0.1700
Data Index: 5761072 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.3828. Min Act: -0.1700
Data Index: 4423882 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.3203. Min Act: -0.1700
Data Index: 8647715 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.3203. Min Act: -0.1700
Data Index: 5409877 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2890. Min Act: -0.1700
Data Index: 4981036 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2890. Min Act: -0.1700
Data Index: 942315 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2890. Min Act: -0.1700
Data Index: 6470142 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2578. Min Act: -0.1700
Data Index: 7069667 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2265. Min Act: -0.1700
Data Index: 98155 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2890. Min Act: -0.1700
Data Index: 7546052 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2265. Min Act: -0.1700
Data Index: 6747063 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.2265. Min Act: -0.1700
Data Index: 5210194 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.1953. Min Act: -0.1700
Data Index: 3195675 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8515. Min Range: -7.8515
Max Act: 7.1640. Min Act: -0.1700
Data Index: 5550167 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19