Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0532. Min Range: -4.0532
Max Act: 4.0532. Min Act: -0.1700
Data Index: 25041 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0532. Min Range: -4.0532
Max Act: 4.0219. Min Act: -0.1700
Data Index: 4755748 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.9906. Min Act: -0.1700
Data Index: 7649246 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.9281. Min Act: -0.1700
Data Index: 6346701 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.9594. Min Act: -0.1700
Data Index: 6075410 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.9281. Min Act: -0.1700
Data Index: 5595207 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.9594. Min Act: -0.1700
Data Index: 2029755 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8969. Min Act: -0.1700
Data Index: 4385723 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8969. Min Act: -0.1700
Data Index: 4394240 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8969. Min Act: -0.1700
Data Index: 8442510 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8969. Min Act: -0.1700
Data Index: 47594 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8343. Min Act: -0.1700
Data Index: 8710800 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8656. Min Act: -0.1700
Data Index: 7157676 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8656. Min Act: -0.1700
Data Index: 224717 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8656. Min Act: -0.1700
Data Index: 38805 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8656. Min Act: -0.1700
Data Index: 4067951 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8343. Min Act: -0.1700
Data Index: 7258876 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8343. Min Act: -0.1700
Data Index: 3588897 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8343. Min Act: -0.1700
Data Index: 7805988 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0532. Min Range: -4.0532
Max Act: 3.8343. Min Act: -0.1700
Data Index: 1768836 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19