Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0377. Min Range: -7.0377
Max Act: 7.0377. Min Act: -0.1700
Data Index: 1040699 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.9440. Min Act: -0.1700
Data Index: 2091788 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.8815. Min Act: -0.1700
Data Index: 7416705 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.8815. Min Act: -0.1700
Data Index: 2254233 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.8190. Min Act: -0.1700
Data Index: 8366912 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.7877. Min Act: -0.1700
Data Index: 2746413 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.7877. Min Act: -0.1700
Data Index: 6606944 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.6940. Min Act: -0.1700
Data Index: 878480 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.6627. Min Act: -0.1700
Data Index: 164306 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.6627. Min Act: -0.1700
Data Index: 6343387 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.6315. Min Act: -0.1700
Data Index: 5162515 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.6002. Min Act: -0.1700
Data Index: 4993007 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5690. Min Act: -0.1700
Data Index: 550487 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5377. Min Act: -0.1700
Data Index: 4895675 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.6002. Min Act: -0.1700
Data Index: 351697 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5377. Min Act: -0.1700
Data Index: 333402 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5377. Min Act: -0.1700
Data Index: 7665296 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5065. Min Act: -0.1700
Data Index: 4889427 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5065. Min Act: -0.1700
Data Index: 3993455 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0377. Min Range: -7.0377
Max Act: 6.5065. Min Act: -0.1700
Data Index: 493528 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19