Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4973 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5855. Min Range: -8.5855
Max Act: 8.5855. Min Act: -0.1700
Data Index: 7528873 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5855. Min Range: -8.5855
Max Act: 8.4605. Min Act: -0.1700
Data Index: 5264585 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5855. Min Range: -8.5855
Max Act: 8.2105. Min Act: -0.1700
Data Index: 8596518 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5855. Min Range: -8.5855
Max Act: 8.0230. Min Act: -0.1700
Data Index: 6117775 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.9918. Min Act: -0.1700
Data Index: 4433573 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.9605. Min Act: -0.1700
Data Index: 7506658 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.9605. Min Act: -0.1700
Data Index: 8279587 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.8355. Min Act: -0.1700
Data Index: 1429229 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.8043. Min Act: -0.1700
Data Index: 5950747 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.7730. Min Act: -0.1699
Data Index: 8265031 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 4680988 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.7418. Min Act: -0.1700
Data Index: 2479482 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 147913 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 4689247 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.6793. Min Act: -0.1700
Data Index: 2589027 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 3416292 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.6793. Min Act: -0.1700
Data Index: 8226419 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 4172490 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.5855. Min Act: -0.1700
Data Index: 4481397 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5855. Min Range: -8.5855
Max Act: 7.6168. Min Act: -0.1700
Data Index: 6441579 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19