Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4445 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2534. Min Range: -7.2534
Max Act: 7.2534. Min Act: -0.1700
Data Index: 8015934 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2534. Min Range: -7.2534
Max Act: 7.0659. Min Act: -0.1700
Data Index: 6191550 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2534. Min Range: -7.2534
Max Act: 7.0347. Min Act: -0.1700
Data Index: 5117276 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2534. Min Range: -7.2534
Max Act: 7.0034. Min Act: -0.1700
Data Index: 6775965 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.9722. Min Act: -0.1700
Data Index: 1355183 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.8784. Min Act: -0.1700
Data Index: 4490489 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.8472. Min Act: -0.1700
Data Index: 1775754 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.8159. Min Act: -0.1700
Data Index: 6507145 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.7534. Min Act: -0.1700
Data Index: 5676177 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.7847. Min Act: -0.1700
Data Index: 5446720 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.7534. Min Act: -0.1700
Data Index: 8109280 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.7222. Min Act: -0.1700
Data Index: 450615 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.6909. Min Act: -0.1700
Data Index: 7873775 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.6597. Min Act: -0.1700
Data Index: 6552668 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.6597. Min Act: -0.1700
Data Index: 5097993 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.6597. Min Act: -0.1700
Data Index: 774216 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.5972. Min Act: -0.1700
Data Index: 1472969 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.6597. Min Act: -0.1700
Data Index: 125212 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.5972. Min Act: -0.1700
Data Index: 5762147 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2534. Min Range: -7.2534
Max Act: 6.5659. Min Act: -0.1700
Data Index: 7750752 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19