Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.5966. Min Act: -0.1700
Data Index: 6697837 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.1591. Min Act: -0.1700
Data Index: 3833228 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.1278. Min Act: -0.1700
Data Index: 4569689 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.1278. Min Act: -0.1700
Data Index: 4133589 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 2716720 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0653. Min Act: -0.1700
Data Index: 2384088 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 3696744 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0341. Min Act: -0.1700
Data Index: 6291827 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 8444698 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 238291 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5966. Min Range: -7.5966
Max Act: 7.0028. Min Act: -0.1700
Data Index: 8554962 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 5790191 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 1308990 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 5804894 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9403. Min Act: -0.1700
Data Index: 5023623 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9403. Min Act: -0.1700
Data Index: 8571068 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 2499947 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9716. Min Act: -0.1700
Data Index: 3298368 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.9091. Min Act: -0.1700
Data Index: 3020496 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5966. Min Range: -7.5966
Max Act: 6.8778. Min Act: -0.1700
Data Index: 721384 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19