Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3349 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.7329. Min Act: -0.1700
Data Index: 6790950 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.7329. Min Act: -0.1700
Data Index: 1203927 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.4829. Min Act: -0.1700
Data Index: 2792694 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.3579. Min Act: -0.1700
Data Index: 4923094 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2954. Min Act: -0.1700
Data Index: 3321438 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2954. Min Act: -0.1700
Data Index: 5203871 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2954. Min Act: -0.1700
Data Index: 7026709 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2954. Min Act: -0.1700
Data Index: 4383604 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2954. Min Act: -0.1700
Data Index: 7964368 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2329. Min Act: -0.1700
Data Index: 3424260 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2954. Min Act: -0.1700
Data Index: 7812572 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2329. Min Act: -0.1700
Data Index: 8137157 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2329. Min Act: -0.1700
Data Index: 956466 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.2329. Min Act: -0.1700
Data Index: 3081557 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.1079. Min Act: -0.1700
Data Index: 1095211 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.1704. Min Act: -0.1700
Data Index: 887045 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.1704. Min Act: -0.1700
Data Index: 5400704 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.1704. Min Act: -0.1700
Data Index: 2073784 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.1704. Min Act: -0.1700
Data Index: 7047187 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7329. Min Range: -9.7329
Max Act: 9.1079. Min Act: -0.1700
Data Index: 2482521 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19