Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1228. Min Range: -3.1228
Max Act: 3.1228. Min Act: -0.1700
Data Index: 1006063 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1228. Min Range: -3.1228
Max Act: 3.0597. Min Act: -0.1700
Data Index: 7263326 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9649. Min Act: -0.1700
Data Index: 7704470 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9966. Min Act: -0.1700
Data Index: 7777371 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9333. Min Act: -0.1700
Data Index: 3647409 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9174. Min Act: -0.1700
Data Index: 3495345 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8857. Min Act: -0.1700
Data Index: 4314274 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9016. Min Act: -0.1700
Data Index: 2021012 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9016. Min Act: -0.1700
Data Index: 3375474 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9016. Min Act: -0.1700
Data Index: 2639112 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.9016. Min Act: -0.1700
Data Index: 2998796 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8698. Min Act: -0.1700
Data Index: 3240966 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8540. Min Act: -0.1700
Data Index: 5524843 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8381. Min Act: -0.1700
Data Index: 2911369 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8540. Min Act: -0.1700
Data Index: 888268 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8381. Min Act: -0.1700
Data Index: 7416842 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8381. Min Act: -0.1700
Data Index: 7845024 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8222. Min Act: -0.1700
Data Index: 8511867 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.8222. Min Act: -0.1700
Data Index: 8346177 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1228. Min Range: -3.1228
Max Act: 2.7903. Min Act: -0.1700
Data Index: 8219850 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19