Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.9068. Min Act: -0.1700
Data Index: 2914047 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.8130. Min Act: -0.1700
Data Index: 6972018 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.7818. Min Act: -0.1700
Data Index: 8661503 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.7193. Min Act: -0.1700
Data Index: 4376110 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.6880. Min Act: -0.1700
Data Index: 6118585 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.6568. Min Act: -0.1700
Data Index: 3763880 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.5943. Min Act: -0.1700
Data Index: 2015108 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.5318. Min Act: -0.1700
Data Index: 7823354 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.4380. Min Act: -0.1700
Data Index: 4286501 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.4068. Min Act: -0.1700
Data Index: 6270183 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.4380. Min Act: -0.1700
Data Index: 3647446 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.4068. Min Act: -0.1700
Data Index: 756116 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.4068. Min Act: -0.1700
Data Index: 1779086 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.4068. Min Act: -0.1700
Data Index: 7445492 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.3755. Min Act: -0.1700
Data Index: 4068567 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.3755. Min Act: -0.1700
Data Index: 4457803 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.3443. Min Act: -0.1700
Data Index: 4091660 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.3443. Min Act: -0.1700
Data Index: 5865901 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.3130. Min Act: -0.1700
Data Index: 3927158 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9068. Min Range: -6.9068
Max Act: 6.3443. Min Act: -0.1700
Data Index: 865259 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19