Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.4899. Min Act: -0.1700
Data Index: 1215912 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.4899. Min Act: -0.1700
Data Index: 7743021 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.3023. Min Act: -0.1700
Data Index: 1967896 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2711. Min Act: -0.1700
Data Index: 5890272 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2711. Min Act: -0.1700
Data Index: 6211313 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2711. Min Act: -0.1700
Data Index: 4862587 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2398. Min Act: -0.1700
Data Index: 1766390 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2711. Min Act: -0.1700
Data Index: 7599671 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2398. Min Act: -0.1700
Data Index: 4033019 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2398. Min Act: -0.1700
Data Index: 663583 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2086. Min Act: -0.1700
Data Index: 7356774 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.2086. Min Act: -0.1700
Data Index: 2116133 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1773. Min Act: -0.1700
Data Index: 443257 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1461. Min Act: -0.1700
Data Index: 6056534 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1773. Min Act: -0.1700
Data Index: 686075 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1461. Min Act: -0.1700
Data Index: 8450917 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1461. Min Act: -0.1700
Data Index: 2589753 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1148. Min Act: -0.1700
Data Index: 6367783 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.1148. Min Act: -0.1700
Data Index: 1284467 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4899. Min Range: -4.4899
Max Act: 4.0836. Min Act: -0.1700
Data Index: 2024504 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19