Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2046 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.2293. Min Act: -0.1700
Data Index: 5932985 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.1668. Min Act: -0.1700
Data Index: 6134045 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.1981. Min Act: -0.1700
Data Index: 345197 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.1043. Min Act: -0.1700
Data Index: 1197462 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.0418. Min Act: -0.1700
Data Index: 8675791 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.0731. Min Act: -0.1700
Data Index: 748297 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2293. Min Range: -7.2293
Max Act: 7.0418. Min Act: -0.1700
Data Index: 3649460 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.9793. Min Act: -0.1700
Data Index: 8134642 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.9168. Min Act: -0.1700
Data Index: 5960530 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.9481. Min Act: -0.1700
Data Index: 7709579 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.8856. Min Act: -0.1700
Data Index: 2646211 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.8856. Min Act: -0.1700
Data Index: 7528950 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.8856. Min Act: -0.1700
Data Index: 1663064 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.8231. Min Act: -0.1700
Data Index: 7965132 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.7918. Min Act: -0.1700
Data Index: 280842 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.7918. Min Act: -0.1700
Data Index: 8819480 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.7606. Min Act: -0.1700
Data Index: 6838314 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.7293. Min Act: -0.1700
Data Index: 4188347 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.7293. Min Act: -0.1700
Data Index: 3023908 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2293. Min Range: -7.2293
Max Act: 6.6981. Min Act: -0.1700
Data Index: 8524091 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19