Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5138 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.8273. Min Act: -0.1700
Data Index: 8621826 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.6517. Min Act: -0.1700
Data Index: 1649241 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.6356. Min Act: -0.1700
Data Index: 8665618 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.6195. Min Act: -0.1700
Data Index: 1320719 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.6195. Min Act: -0.1700
Data Index: 672959 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.6035. Min Act: -0.1700
Data Index: 4181237 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.6035. Min Act: -0.1700
Data Index: 7443143 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5712. Min Act: -0.1700
Data Index: 2277157 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5874. Min Act: -0.1700
Data Index: 314104 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5712. Min Act: -0.1700
Data Index: 4536044 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5390. Min Act: -0.1700
Data Index: 6726975 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5551. Min Act: -0.1700
Data Index: 3839118 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5228. Min Act: -0.1700
Data Index: 1889896 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5712. Min Act: -0.1700
Data Index: 6780021 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5228. Min Act: -0.1700
Data Index: 724933 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5066. Min Act: -0.1700
Data Index: 3355715 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.5066. Min Act: -0.1700
Data Index: 8776615 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.4742. Min Act: -0.1700
Data Index: 900206 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.4904. Min Act: -0.1700
Data Index: 1258538 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8273. Min Range: -2.8273
Max Act: 2.4904. Min Act: -0.1700
Data Index: 7830407 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19