Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0128. Min Range: -6.0128
Max Act: 6.0128. Min Act: -0.1700
Data Index: 4109309 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.8878. Min Act: -0.1700
Data Index: 8387901 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7941. Min Act: -0.1700
Data Index: 4009492 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7628. Min Act: -0.1700
Data Index: 7788438 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7628. Min Act: -0.1700
Data Index: 1616304 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7316. Min Act: -0.1700
Data Index: 413655 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7628. Min Act: -0.1700
Data Index: 3246216 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7628. Min Act: -0.1700
Data Index: 3282278 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7003. Min Act: -0.1700
Data Index: 413656 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7316. Min Act: -0.1700
Data Index: 2819943 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7316. Min Act: -0.1700
Data Index: 5767085 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7316. Min Act: -0.1700
Data Index: 6728709 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.7003. Min Act: -0.1700
Data Index: 7419478 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6691. Min Act: -0.1700
Data Index: 6831784 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6691. Min Act: -0.1700
Data Index: 7990752 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6691. Min Act: -0.1700
Data Index: 1326925 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6378. Min Act: -0.1700
Data Index: 6450479 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6378. Min Act: -0.1700
Data Index: 6301350 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6378. Min Act: -0.1700
Data Index: 5871860 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0128. Min Range: -6.0128
Max Act: 5.6378. Min Act: -0.1700
Data Index: 1104908 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19