Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2132 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2984. Min Act: -0.1700
Data Index: 6942248 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 3545866 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 6829121 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2046. Min Act: -0.1700
Data Index: 7860980 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1733. Min Act: -0.1700
Data Index: 2882203 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.2358. Min Act: -0.1700
Data Index: 304551 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1733. Min Act: -0.1700
Data Index: 6978000 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1733. Min Act: -0.1700
Data Index: 2800598 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 2409520 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 1516111 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 7887796 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 5602876 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 2361696 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1108. Min Act: -0.1700
Data Index: 7155160 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1421. Min Act: -0.1700
Data Index: 4949956 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 3767995 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 5412091 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.1108. Min Act: -0.1700
Data Index: 6498046 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 1268320 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2984. Min Range: -4.2984
Max Act: 4.0796. Min Act: -0.1700
Data Index: 5560400 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19