Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 874 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.4213. Min Act: -0.1700
Data Index: 6563967 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3743. Min Act: -0.1700
Data Index: 5402499 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.3272. Min Act: -0.1700
Data Index: 6138715 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2487. Min Act: -0.1700
Data Index: 1030428 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2644. Min Act: -0.1700
Data Index: 4401772 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2487. Min Act: -0.1700
Data Index: 4385517 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1858. Min Act: -0.1700
Data Index: 1972845 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2173. Min Act: -0.1700
Data Index: 746310 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.2016. Min Act: -0.1700
Data Index: 6978108 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1858. Min Act: -0.1700
Data Index: 1972848 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1701. Min Act: -0.1700
Data Index: 2547529 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1544. Min Act: -0.1700
Data Index: 5402506 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1229. Min Act: -0.1700
Data Index: 6358351 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1386. Min Act: -0.1700
Data Index: 1030440 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1386. Min Act: -0.1700
Data Index: 1254939 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0914. Min Act: -0.1700
Data Index: 7419642 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.1229. Min Act: -0.1700
Data Index: 4536814 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0914. Min Act: -0.1700
Data Index: 2954052 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0914. Min Act: -0.1700
Data Index: 5402503 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4213. Min Range: -3.4213
Max Act: 3.0914. Min Act: -0.1700
Data Index: 1346081 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19