Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6334 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1426. Min Range: -8.1426
Max Act: 8.1426. Min Act: -0.1700
Data Index: 5637236 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1426. Min Range: -8.1426
Max Act: 8.1114. Min Act: -0.1700
Data Index: 7831175 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1426. Min Range: -8.1426
Max Act: 8.1114. Min Act: -0.1700
Data Index: 7310158 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.9239. Min Act: -0.1700
Data Index: 6813925 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.8301. Min Act: -0.1700
Data Index: 6290730 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.6739. Min Act: -0.1700
Data Index: 3819137 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.6739. Min Act: -0.1700
Data Index: 4042662 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.6426. Min Act: -0.1700
Data Index: 3404352 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.5801. Min Act: -0.1700
Data Index: 8709789 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.6114. Min Act: -0.1700
Data Index: 8744533 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.5801. Min Act: -0.1700
Data Index: 8795265 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.5801. Min Act: -0.1700
Data Index: 5882459 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.5176. Min Act: -0.1700
Data Index: 3124021 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.4864. Min Act: -0.1700
Data Index: 4658101 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.5176. Min Act: -0.1700
Data Index: 7725661 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.4864. Min Act: -0.1700
Data Index: 5882249 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.4864. Min Act: -0.1700
Data Index: 2485863 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.4551. Min Act: -0.1700
Data Index: 2209344 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.4239. Min Act: -0.1700
Data Index: 4596137 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1426. Min Range: -8.1426
Max Act: 7.4864. Min Act: -0.1700
Data Index: 5482323 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19