Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3074. Min Range: -7.3074
Max Act: 7.3074. Min Act: -0.1700
Data Index: 8821779 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3074. Min Range: -7.3074
Max Act: 7.2449. Min Act: -0.1700
Data Index: 7792240 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3074. Min Range: -7.3074
Max Act: 7.0886. Min Act: -0.1700
Data Index: 283372 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.9949. Min Act: -0.1700
Data Index: 1436583 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.9636. Min Act: -0.1700
Data Index: 3393208 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.9324. Min Act: -0.1700
Data Index: 986106 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.9011. Min Act: -0.1700
Data Index: 2926455 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.9011. Min Act: -0.1700
Data Index: 4472135 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.8699. Min Act: -0.1700
Data Index: 6615910 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.8386. Min Act: -0.1700
Data Index: 5056519 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.8699. Min Act: -0.1700
Data Index: 1319590 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.8074. Min Act: -0.1700
Data Index: 8417519 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7761. Min Act: -0.1700
Data Index: 6981500 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7761. Min Act: -0.1700
Data Index: 8718904 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7449. Min Act: -0.1700
Data Index: 1691158 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7449. Min Act: -0.1700
Data Index: 2026461 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7136. Min Act: -0.1700
Data Index: 7545196 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7136. Min Act: -0.1700
Data Index: 5106071 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.6824. Min Act: -0.1700
Data Index: 7766985 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3074. Min Range: -7.3074
Max Act: 6.7136. Min Act: -0.1700
Data Index: 6516119 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19