Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2446 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0486. Min Range: -3.0486
Max Act: 3.0486. Min Act: -0.1700
Data Index: 2630876 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0486. Min Range: -3.0486
Max Act: 3.0013. Min Act: -0.1700
Data Index: 3130434 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9854. Min Act: -0.1700
Data Index: 6469974 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.9221. Min Act: -0.1700
Data Index: 5987083 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8904. Min Act: -0.1700
Data Index: 2005065 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8904. Min Act: -0.1700
Data Index: 3758434 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8904. Min Act: -0.1700
Data Index: 2073601 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 1815222 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8746. Min Act: -0.1700
Data Index: 1417684 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8587. Min Act: -0.1700
Data Index: 2547490 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8269. Min Act: -0.1700
Data Index: 867118 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8428. Min Act: -0.1700
Data Index: 7779522 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8269. Min Act: -0.1700
Data Index: 2630875 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8269. Min Act: -0.1700
Data Index: 8682476 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8269. Min Act: -0.1700
Data Index: 6681898 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8110. Min Act: -0.1700
Data Index: 1827978 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8269. Min Act: -0.1700
Data Index: 6318400 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8110. Min Act: -0.1700
Data Index: 1815021 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8110. Min Act: -0.1700
Data Index: 6698274 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0486. Min Range: -3.0486
Max Act: 2.8110. Min Act: -0.1700
Data Index: 2421137 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19