Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 932 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9542. Min Range: -7.9542
Max Act: 7.9542. Min Act: -0.1700
Data Index: 6288083 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9542. Min Range: -7.9542
Max Act: 4.4229. Min Act: -0.1700
Data Index: 1032093 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.3292. Min Act: -0.1700
Data Index: 737929 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.3292. Min Act: -0.1700
Data Index: 5794748 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.2979. Min Act: -0.1700
Data Index: 814537 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.4542. Min Act: -0.1700
Data Index: 2292950 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.1729. Min Act: -0.1700
Data Index: 8108331 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.1104. Min Act: -0.1700
Data Index: 113363 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.3917. Min Act: -0.1700
Data Index: 5856911 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.0167. Min Act: -0.1700
Data Index: 6070912 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.1104. Min Act: -0.1700
Data Index: 6962855 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.9854. Min Act: -0.1700
Data Index: 1411893 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.9542. Min Act: -0.1700
Data Index: 2298994 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.9229. Min Act: -0.1700
Data Index: 4917578 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.8917. Min Act: -0.1700
Data Index: 1227611 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 2711054 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 7347634 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9542. Min Range: -7.9542
Max Act: 6.0479. Min Act: -0.1700
Data Index: 5853593 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1050828 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9542. Min Range: -7.9542
Max Act: 5.4542. Min Act: -0.1700
Data Index: 16741 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19