Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3422 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.7156. Min Act: -0.1700
Data Index: 432973 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 2872128 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.6531. Min Act: -0.1700
Data Index: 2193742 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.4969. Min Act: -0.1700
Data Index: 4454537 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.4969. Min Act: -0.1700
Data Index: 7880581 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.3406. Min Act: -0.1700
Data Index: 5686491 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.3094. Min Act: -0.1700
Data Index: 3477 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.3094. Min Act: -0.1700
Data Index: 6793202 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.3406. Min Act: -0.1700
Data Index: 479051 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.3094. Min Act: -0.1700
Data Index: 6718844 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.3094. Min Act: -0.1700
Data Index: 2572703 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2781. Min Act: -0.1700
Data Index: 4193292 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2469. Min Act: -0.1700
Data Index: 917088 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2156. Min Act: -0.1700
Data Index: 1564767 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.1844. Min Act: -0.1700
Data Index: 1262833 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2156. Min Act: -0.1700
Data Index: 7124058 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2156. Min Act: -0.1700
Data Index: 7766315 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2156. Min Act: -0.1700
Data Index: 6427186 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.2156. Min Act: -0.1700
Data Index: 432975 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7156. Min Range: -6.7156
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4951268 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19