Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3145 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.6142. Min Act: -0.1700
Data Index: 6703608 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.5012. Min Act: -0.1700
Data Index: 7204373 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.4200. Min Act: -0.1700
Data Index: 2881653 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.4200. Min Act: -0.1700
Data Index: 3068889 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3873. Min Act: -0.1700
Data Index: 2500795 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3710. Min Act: -0.1699
Data Index: 721801 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3710. Min Act: -0.1700
Data Index: 7310858 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3546. Min Act: -0.1700
Data Index: 1924715 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3546. Min Act: -0.1700
Data Index: 6652518 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3546. Min Act: -0.1700
Data Index: 5777469 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3546. Min Act: -0.1700
Data Index: 5891512 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3218. Min Act: -0.1700
Data Index: 1928575 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3218. Min Act: -0.1699
Data Index: 8739562 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3054. Min Act: -0.1700
Data Index: 5694029 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3054. Min Act: -0.1700
Data Index: 2649834 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.3054. Min Act: -0.1700
Data Index: 7537337 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.2889. Min Act: -0.1700
Data Index: 8153443 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.2889. Min Act: -0.1700
Data Index: 2012674 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.2889. Min Act: -0.1700
Data Index: 7403734 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6142. Min Range: -2.6142
Max Act: 2.2889. Min Act: -0.1700
Data Index: 5279254 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19