Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4968 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.5004. Min Act: -0.1700
Data Index: 7866624 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.4691. Min Act: -0.1700
Data Index: 569100 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.3441. Min Act: -0.1700
Data Index: 5520764 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.2503. Min Act: -0.1700
Data Index: 2490877 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1878. Min Act: -0.1700
Data Index: 7344482 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1878. Min Act: -0.1700
Data Index: 2674426 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1566. Min Act: -0.1700
Data Index: 4691620 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1253. Min Act: -0.1700
Data Index: 2655730 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1253. Min Act: -0.1700
Data Index: 1649732 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.1253. Min Act: -0.1700
Data Index: 4587216 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2026911 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.0941. Min Act: -0.1700
Data Index: 2674425 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.0628. Min Act: -0.1700
Data Index: 7056657 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.0316. Min Act: -0.1700
Data Index: 4316702 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5004. Min Range: -4.5004
Max Act: 4.0003. Min Act: -0.1700
Data Index: 3067939 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.9378. Min Act: -0.1700
Data Index: 1168728 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.9690. Min Act: -0.1700
Data Index: 3254940 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.9690. Min Act: -0.1700
Data Index: 1153600 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.9690. Min Act: -0.1700
Data Index: 3406720 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5004. Min Range: -4.5004
Max Act: 3.9378. Min Act: -0.1700
Data Index: 1909944 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19