Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 900 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0021. Min Range: -5.0021
Max Act: 5.0021. Min Act: -0.1700
Data Index: 5891005 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.9396. Min Act: -0.1700
Data Index: 5958426 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.8459. Min Act: -0.1700
Data Index: 7433333 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.8459. Min Act: -0.1700
Data Index: 5715042 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.8146. Min Act: -0.1700
Data Index: 4229384 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7834. Min Act: -0.1700
Data Index: 1637397 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7834. Min Act: -0.1700
Data Index: 4649294 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7521. Min Act: -0.1700
Data Index: 2119005 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7521. Min Act: -0.1700
Data Index: 4644560 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7521. Min Act: -0.1700
Data Index: 1124409 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7521. Min Act: -0.1700
Data Index: 4434296 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7209. Min Act: -0.1700
Data Index: 8333698 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7209. Min Act: -0.1700
Data Index: 7230426 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7209. Min Act: -0.1700
Data Index: 1016446 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.6896. Min Act: -0.1700
Data Index: 1405519 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.7209. Min Act: -0.1700
Data Index: 7945187 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.6896. Min Act: -0.1700
Data Index: 2956300 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.6896. Min Act: -0.1700
Data Index: 5745868 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.6896. Min Act: -0.1700
Data Index: 5216319 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0021. Min Range: -5.0021
Max Act: 4.6896. Min Act: -0.1700
Data Index: 6243332 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19