Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.4691. Min Act: -0.1700
Data Index: 6665300 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.3753. Min Act: -0.1700
Data Index: 5252967 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.2816. Min Act: -0.1700
Data Index: 5625379 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.2191. Min Act: -0.1700
Data Index: 2346756 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.1878. Min Act: -0.1700
Data Index: 5567914 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.1566. Min Act: -0.1700
Data Index: 6808136 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.1253. Min Act: -0.1700
Data Index: 3711643 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.1253. Min Act: -0.1700
Data Index: 4480933 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.1253. Min Act: -0.1700
Data Index: 8425832 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 7108437 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 3489208 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 3660853 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 3805287 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 3306492 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 7377970 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 2394961 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 4498916 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0941. Min Act: -0.1700
Data Index: 487481 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0628. Min Act: -0.1700
Data Index: 2312628 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4691. Min Range: -5.4691
Max Act: 5.0316. Min Act: -0.1700
Data Index: 465563 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19