Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4347 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.6164. Min Act: -0.1700
Data Index: 812267 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3976. Min Act: -0.1700
Data Index: 3624019 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3976. Min Act: -0.1700
Data Index: 1040829 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3976. Min Act: -0.1700
Data Index: 3552663 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.4289. Min Act: -0.1700
Data Index: 8558153 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3039. Min Act: -0.1700
Data Index: 990073 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.3039. Min Act: -0.1700
Data Index: 8065826 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.2414. Min Act: -0.1700
Data Index: 134419 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.2726. Min Act: -0.1700
Data Index: 5859406 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.2414. Min Act: -0.1700
Data Index: 857437 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.2726. Min Act: -0.1700
Data Index: 5131424 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1789. Min Act: -0.1700
Data Index: 7554099 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.2101. Min Act: -0.1700
Data Index: 7492583 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1789. Min Act: -0.1700
Data Index: 1461415 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1789. Min Act: -0.1700
Data Index: 8326438 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1476. Min Act: -0.1700
Data Index: 4383396 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1476. Min Act: -0.1700
Data Index: 5495244 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1476. Min Act: -0.1700
Data Index: 2118209 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.1164. Min Act: -0.1700
Data Index: 6108947 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6164. Min Range: -6.6164
Max Act: 6.0539. Min Act: -0.1700
Data Index: 1394232 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19