Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.7136. Min Act: -0.1700
Data Index: 5795793 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.7136. Min Act: -0.1700
Data Index: 6666719 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.6511. Min Act: -0.1700
Data Index: 7275754 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4636. Min Act: -0.1700
Data Index: 7811928 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4636. Min Act: -0.1700
Data Index: 3262689 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4636. Min Act: -0.1700
Data Index: 7189948 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4636. Min Act: -0.1700
Data Index: 6130188 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 4891134 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 4830434 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 8223920 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 2519054 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 2307460 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 8110633 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.4011. Min Act: -0.1700
Data Index: 7310173 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.2761. Min Act: -0.1700
Data Index: 2699670 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.2761. Min Act: -0.1700
Data Index: 8207169 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.2761. Min Act: -0.1700
Data Index: 1252587 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.2761. Min Act: -0.1700
Data Index: 2796177 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.2761. Min Act: -0.1700
Data Index: 1840520 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7136. Min Range: -8.7136
Max Act: 8.2136. Min Act: -0.1700
Data Index: 901876 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19