Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5228 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.6862. Min Act: -0.1700
Data Index: 7765585 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.6862. Min Act: -0.1700
Data Index: 1706296 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.4987. Min Act: -0.1700
Data Index: 6639304 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3737. Min Act: -0.1700
Data Index: 7205264 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3112. Min Act: -0.1700
Data Index: 7024282 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3737. Min Act: -0.1700
Data Index: 2938134 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3737. Min Act: -0.1700
Data Index: 8077582 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3112. Min Act: -0.1700
Data Index: 6618466 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3112. Min Act: -0.1700
Data Index: 7750589 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.3112. Min Act: -0.1700
Data Index: 3617272 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.2487. Min Act: -0.1700
Data Index: 7852309 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.2487. Min Act: -0.1700
Data Index: 1515682 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.2487. Min Act: -0.1700
Data Index: 6576803 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1862. Min Act: -0.1700
Data Index: 3394290 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1862. Min Act: -0.1700
Data Index: 7520711 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1862. Min Act: -0.1700
Data Index: 6456902 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1237. Min Act: -0.1700
Data Index: 3919592 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1862. Min Act: -0.1700
Data Index: 2587302 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1862. Min Act: -0.1700
Data Index: 5973556 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6862. Min Range: -8.6862
Max Act: 8.1237. Min Act: -0.1700
Data Index: 1368286 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19