Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1041. Min Range: -4.1041
Max Act: 4.1041. Min Act: -0.1700
Data Index: 731462 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.9165. Min Act: -0.1700
Data Index: 7610213 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.8227. Min Act: -0.1700
Data Index: 675275 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.7914. Min Act: -0.1700
Data Index: 7815427 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.7602. Min Act: -0.1700
Data Index: 3409672 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.7289. Min Act: -0.1700
Data Index: 4794258 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.6976. Min Act: -0.1700
Data Index: 2801008 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.6976. Min Act: -0.1700
Data Index: 6876924 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.6663. Min Act: -0.1700
Data Index: 163588 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.6663. Min Act: -0.1700
Data Index: 7520737 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.6663. Min Act: -0.1700
Data Index: 6005932 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.6507. Min Act: -0.1700
Data Index: 4600953 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5881. Min Act: -0.1700
Data Index: 3178450 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5567. Min Act: -0.1700
Data Index: 8391412 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5724. Min Act: -0.1700
Data Index: 906996 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5567. Min Act: -0.1700
Data Index: 6595113 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5411. Min Act: -0.1700
Data Index: 1371103 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5411. Min Act: -0.1700
Data Index: 2148742 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5254. Min Act: -0.1700
Data Index: 356294 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1041. Min Range: -4.1041
Max Act: 3.5254. Min Act: -0.1700
Data Index: 3748030 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19