Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3168 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0184. Min Range: -8.0184
Max Act: 8.0184. Min Act: -0.1700
Data Index: 2473538 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.8934. Min Act: -0.1700
Data Index: 4254661 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.7684. Min Act: -0.1700
Data Index: 6109659 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.7059. Min Act: -0.1700
Data Index: 7235247 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.7684. Min Act: -0.1700
Data Index: 7594023 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.6434. Min Act: -0.1700
Data Index: 2287571 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.5809. Min Act: -0.1700
Data Index: 2403223 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.5809. Min Act: -0.1700
Data Index: 1573954 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.5496. Min Act: -0.1700
Data Index: 2938352 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.5496. Min Act: -0.1700
Data Index: 2963581 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.5496. Min Act: -0.1700
Data Index: 1312409 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.5184. Min Act: -0.1700
Data Index: 3990929 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4871. Min Act: -0.1700
Data Index: 2465228 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4871. Min Act: -0.1700
Data Index: 8540927 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4559. Min Act: -0.1700
Data Index: 5458901 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4246. Min Act: -0.1700
Data Index: 7200447 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4246. Min Act: -0.1700
Data Index: 4160692 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4246. Min Act: -0.1700
Data Index: 7685489 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4246. Min Act: -0.1700
Data Index: 3297946 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0184. Min Range: -8.0184
Max Act: 7.4246. Min Act: -0.1700
Data Index: 7535917 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19