Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.5729. Min Act: -0.1700
Data Index: 8159865 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.5104. Min Act: -0.1700
Data Index: 8545333 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.4479. Min Act: -0.1700
Data Index: 2972834 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.4166. Min Act: -0.1700
Data Index: 2353782 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.4166. Min Act: -0.1700
Data Index: 6788091 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.4479. Min Act: -0.1700
Data Index: 3668608 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3854. Min Act: -0.1700
Data Index: 1258429 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3854. Min Act: -0.1700
Data Index: 6338093 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3541. Min Act: -0.1700
Data Index: 8225896 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3541. Min Act: -0.1700
Data Index: 5108942 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3541. Min Act: -0.1700
Data Index: 6282992 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2916. Min Act: -0.1700
Data Index: 4237321 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3229. Min Act: -0.1700
Data Index: 1090287 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3229. Min Act: -0.1700
Data Index: 4158732 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.3229. Min Act: -0.1700
Data Index: 4660771 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2604. Min Act: -0.1700
Data Index: 8760475 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2604. Min Act: -0.1700
Data Index: 1272568 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2291. Min Act: -0.1700
Data Index: 7436840 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2291. Min Act: -0.1700
Data Index: 6939219 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5729. Min Range: -6.5729
Max Act: 6.2291. Min Act: -0.1700
Data Index: 3298226 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19