Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5465 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.4843. Min Act: -0.1700
Data Index: 2531613 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.4530. Min Act: -0.1700
Data Index: 4705306 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.3905. Min Act: -0.1700
Data Index: 1167587 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.3593. Min Act: -0.1700
Data Index: 988014 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.2968. Min Act: -0.1700
Data Index: 406423 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.2655. Min Act: -0.1700
Data Index: 8091703 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.2343. Min Act: -0.1700
Data Index: 7340885 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.2343. Min Act: -0.1700
Data Index: 7741091 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.2030. Min Act: -0.1700
Data Index: 6900121 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1717. Min Act: -0.1700
Data Index: 352446 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1717. Min Act: -0.1700
Data Index: 3950732 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1405. Min Act: -0.1700
Data Index: 975040 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1405. Min Act: -0.1700
Data Index: 4570425 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1405. Min Act: -0.1700
Data Index: 4808357 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1092. Min Act: -0.1700
Data Index: 4647282 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.0780. Min Act: -0.1700
Data Index: 4510668 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1092. Min Act: -0.1700
Data Index: 2676153 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1092. Min Act: -0.1700
Data Index: 2139642 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1092. Min Act: -0.1700
Data Index: 7164590 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4843. Min Range: -4.4843
Max Act: 4.1092. Min Act: -0.1700
Data Index: 1078863 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19