Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0022. Min Range: -6.0022
Max Act: 6.0022. Min Act: -0.1700
Data Index: 2849926 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.9397. Min Act: -0.1700
Data Index: 5885120 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.8772. Min Act: -0.1700
Data Index: 935231 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5628360 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.8147. Min Act: -0.1700
Data Index: 3194942 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.8147. Min Act: -0.1700
Data Index: 1956553 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.7210. Min Act: -0.1700
Data Index: 313717 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.6585. Min Act: -0.1700
Data Index: 5575384 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.6897. Min Act: -0.1700
Data Index: 3958258 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.6585. Min Act: -0.1700
Data Index: 2905724 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.6585. Min Act: -0.1700
Data Index: 5119548 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.6272. Min Act: -0.1700
Data Index: 3852951 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5960. Min Act: -0.1700
Data Index: 2251937 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6872761 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3147400 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5647. Min Act: -0.1700
Data Index: 793458 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3826162 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5960. Min Act: -0.1700
Data Index: 6612849 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5335. Min Act: -0.1700
Data Index: 7375903 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0022. Min Range: -6.0022
Max Act: 5.5022. Min Act: -0.1700
Data Index: 6068051 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19