Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.5506. Min Act: -0.1700
Data Index: 151861 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.5193. Min Act: -0.1700
Data Index: 1666037 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.4568. Min Act: -0.1700
Data Index: 4424960 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.3943. Min Act: -0.1700
Data Index: 6676088 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.3943. Min Act: -0.1700
Data Index: 8586018 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.3318. Min Act: -0.1700
Data Index: 4789048 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2693. Min Act: -0.1700
Data Index: 8678830 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2693. Min Act: -0.1700
Data Index: 3804796 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2381. Min Act: -0.1700
Data Index: 5195366 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2068. Min Act: -0.1700
Data Index: 2081859 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2381. Min Act: -0.1700
Data Index: 2359284 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1756. Min Act: -0.1700
Data Index: 8034170 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1756. Min Act: -0.1700
Data Index: 220826 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1756. Min Act: -0.1700
Data Index: 3658379 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2068. Min Act: -0.1700
Data Index: 8650657 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.2068. Min Act: -0.1700
Data Index: 3864202 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1443. Min Act: -0.1700
Data Index: 5051137 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1756. Min Act: -0.1700
Data Index: 2250006 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1131. Min Act: -0.1700
Data Index: 3365873 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5506. Min Range: -6.5506
Max Act: 6.1443. Min Act: -0.1700
Data Index: 3901404 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19