Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3895. Min Range: -4.3895
Max Act: 4.3895. Min Act: -0.1700
Data Index: 798106 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3895. Min Range: -4.3895
Max Act: 4.2333. Min Act: -0.1700
Data Index: 3303253 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3895. Min Range: -4.3895
Max Act: 4.2020. Min Act: -0.1700
Data Index: 1771883 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3895. Min Range: -4.3895
Max Act: 4.0457. Min Act: -0.1700
Data Index: 1932604 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.9207. Min Act: -0.1700
Data Index: 7644399 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.9207. Min Act: -0.1700
Data Index: 680945 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.8894. Min Act: -0.1700
Data Index: 4878777 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.8582. Min Act: -0.1700
Data Index: 7671489 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.8582. Min Act: -0.1700
Data Index: 1482615 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.8582. Min Act: -0.1700
Data Index: 4118039 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.8269. Min Act: -0.1700
Data Index: 4606559 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.8269. Min Act: -0.1700
Data Index: 287251 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7956. Min Act: -0.1700
Data Index: 4547617 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7643. Min Act: -0.1700
Data Index: 161292 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7643. Min Act: -0.1700
Data Index: 3579513 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7643. Min Act: -0.1700
Data Index: 6495278 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 1886140 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7018. Min Act: -0.1700
Data Index: 238428 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 3502616 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3895. Min Range: -4.3895
Max Act: 3.7331. Min Act: -0.1700
Data Index: 4809328 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19