Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.6263. Min Act: -0.1700
Data Index: 6456592 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.6263. Min Act: -0.1700
Data Index: 1834904 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5638. Min Act: -0.1700
Data Index: 6599565 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5951. Min Act: -0.1700
Data Index: 405480 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5951. Min Act: -0.1700
Data Index: 4337601 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5951. Min Act: -0.1700
Data Index: 1712661 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5638. Min Act: -0.1700
Data Index: 1105196 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5326. Min Act: -0.1700
Data Index: 5798780 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5326. Min Act: -0.1700
Data Index: 3694476 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5326. Min Act: -0.1700
Data Index: 3785207 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5326. Min Act: -0.1700
Data Index: 8249786 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5013. Min Act: -0.1700
Data Index: 5648805 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5013. Min Act: -0.1700
Data Index: 71962 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5013. Min Act: -0.1700
Data Index: 1921597 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5013. Min Act: -0.1700
Data Index: 4910138 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.5326. Min Act: -0.1700
Data Index: 5100399 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.4701. Min Act: -0.1700
Data Index: 8161824 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.4701. Min Act: -0.1700
Data Index: 3315770 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.4701. Min Act: -0.1700
Data Index: 1812975 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6263. Min Range: -4.6263
Max Act: 4.4701. Min Act: -0.1700
Data Index: 7663435 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19