Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.3105. Min Act: -0.1700
Data Index: 1549558 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.1855. Min Act: -0.1700
Data Index: 1118198 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0605. Min Act: -0.1700
Data Index: 3403303 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0605. Min Act: -0.1700
Data Index: 655265 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9667. Min Act: -0.1700
Data Index: 8708510 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9667. Min Act: -0.1700
Data Index: 6980125 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 3743355 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9042. Min Act: -0.1700
Data Index: 4441674 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 3203978 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9667. Min Act: -0.1700
Data Index: 6037412 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 7539523 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 5341772 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 567882 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 4874607 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9042. Min Act: -0.1700
Data Index: 1596143 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.8730. Min Act: -0.1700
Data Index: 7981378 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9042. Min Act: -0.1700
Data Index: 8694748 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9042. Min Act: -0.1700
Data Index: 6897054 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9042. Min Act: -0.1700
Data Index: 5611855 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 7252439 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19