Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2979 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0145. Min Range: -7.0145
Max Act: 7.0145. Min Act: -0.1700
Data Index: 679 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0145. Min Range: -7.0145
Max Act: 7.0145. Min Act: -0.1700
Data Index: 7679481 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.9520. Min Act: -0.1700
Data Index: 5146895 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.8270. Min Act: -0.1700
Data Index: 7381015 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.8270. Min Act: -0.1700
Data Index: 6759620 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.7332. Min Act: -0.1700
Data Index: 5575645 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.6707. Min Act: -0.1700
Data Index: 261065 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.6707. Min Act: -0.1700
Data Index: 5268883 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.6395. Min Act: -0.1700
Data Index: 1078861 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.6082. Min Act: -0.1700
Data Index: 6958128 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.6082. Min Act: -0.1700
Data Index: 5643184 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.5457. Min Act: -0.1700
Data Index: 916270 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.5770. Min Act: -0.1700
Data Index: 1068944 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.5145. Min Act: -0.1700
Data Index: 7085317 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.5145. Min Act: -0.1700
Data Index: 7021903 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.4832. Min Act: -0.1700
Data Index: 1174130 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.4207. Min Act: -0.1700
Data Index: 6432546 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.3895. Min Act: -0.1700
Data Index: 1663359 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.3582. Min Act: -0.1700
Data Index: 5752826 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0145. Min Range: -7.0145
Max Act: 6.3582. Min Act: -0.1700
Data Index: 3350889 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19