Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1058 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0546. Min Range: -8.0546
Max Act: 8.0546. Min Act: -0.1700
Data Index: 7070095 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.9921. Min Act: -0.1700
Data Index: 5363834 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.8671. Min Act: -0.1700
Data Index: 1687406 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.8359. Min Act: -0.1700
Data Index: 3276189 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.7734. Min Act: -0.1700
Data Index: 7434959 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.6484. Min Act: -0.1700
Data Index: 5491846 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.6484. Min Act: -0.1700
Data Index: 1939228 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.6484. Min Act: -0.1700
Data Index: 6484815 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.6484. Min Act: -0.1700
Data Index: 2048789 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5546. Min Act: -0.1700
Data Index: 2173724 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.6171. Min Act: -0.1700
Data Index: 7633367 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5859. Min Act: -0.1700
Data Index: 7266674 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5859. Min Act: -0.1700
Data Index: 2565467 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5859. Min Act: -0.1700
Data Index: 1374665 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5546. Min Act: -0.1700
Data Index: 6909736 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5546. Min Act: -0.1700
Data Index: 2881219 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5546. Min Act: -0.1700
Data Index: 3760314 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5234. Min Act: -0.1700
Data Index: 7478335 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.5234. Min Act: -0.1700
Data Index: 5300889 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0546. Min Range: -8.0546
Max Act: 7.4921. Min Act: -0.1700
Data Index: 5205702 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19