Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.8373. Min Act: -0.1700
Data Index: 8605578 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.8373. Min Act: -0.1700
Data Index: 1999743 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.5873. Min Act: -0.1700
Data Index: 41360 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.5248. Min Act: -0.1700
Data Index: 6004000 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.4623. Min Act: -0.1700
Data Index: 3034351 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.3998. Min Act: -0.1700
Data Index: 3311895 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.3373. Min Act: -0.1700
Data Index: 7827582 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.2748. Min Act: -0.1700
Data Index: 5937378 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.3373. Min Act: -0.1700
Data Index: 6638159 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.2748. Min Act: -0.1700
Data Index: 115692 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.2748. Min Act: -0.1697
Data Index: 4091159 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.2123. Min Act: -0.1700
Data Index: 4612382 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.2123. Min Act: -0.1700
Data Index: 7951465 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.1498. Min Act: -0.1700
Data Index: 3684051 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.0873. Min Act: -0.1700
Data Index: 8590894 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.0873. Min Act: -0.1700
Data Index: 776157 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.0873. Min Act: -0.1700
Data Index: 8148293 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.0248. Min Act: -0.1700
Data Index: 3199875 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.0248. Min Act: -0.1700
Data Index: 6545275 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.8373. Min Range: -15.8373
Max Act: 15.0248. Min Act: -0.1700
Data Index: 1209985 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19