Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3290. Min Range: -6.3290
Max Act: 6.3290. Min Act: -0.1700
Data Index: 6773859 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3290. Min Range: -6.3290
Max Act: 6.1103. Min Act: -0.1700
Data Index: 3504089 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3290. Min Range: -6.3290
Max Act: 6.0790. Min Act: -0.1700
Data Index: 5734086 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3290. Min Range: -6.3290
Max Act: 6.0478. Min Act: -0.1700
Data Index: 16751 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3290. Min Range: -6.3290
Max Act: 6.0478. Min Act: -0.1700
Data Index: 5306058 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.9853. Min Act: -0.1700
Data Index: 2290001 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.9540. Min Act: -0.1700
Data Index: 4849600 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8915. Min Act: -0.1700
Data Index: 8356482 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8915. Min Act: -0.1700
Data Index: 5972139 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8915. Min Act: -0.1700
Data Index: 4870354 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8603. Min Act: -0.1700
Data Index: 5043941 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8603. Min Act: -0.1700
Data Index: 6170906 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8290. Min Act: -0.1700
Data Index: 6158913 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.8290. Min Act: -0.1700
Data Index: 181580 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.7665. Min Act: -0.1700
Data Index: 1399918 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.7665. Min Act: -0.1700
Data Index: 6419520 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.7353. Min Act: -0.1700
Data Index: 7430994 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.7665. Min Act: -0.1700
Data Index: 3878381 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.7665. Min Act: -0.1700
Data Index: 4242444 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3290. Min Range: -6.3290
Max Act: 5.7665. Min Act: -0.1700
Data Index: 8257325 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19