Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.4603. Min Act: -0.1700
Data Index: 453279 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.3819. Min Act: -0.1700
Data Index: 8338111 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.3505. Min Act: -0.1700
Data Index: 2681448 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.3034. Min Act: -0.1700
Data Index: 4539060 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2877. Min Act: -0.1700
Data Index: 1626539 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.3034. Min Act: -0.1700
Data Index: 3178158 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2406. Min Act: -0.1700
Data Index: 7245320 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2563. Min Act: -0.1700
Data Index: 1900839 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2563. Min Act: -0.1700
Data Index: 4863398 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2406. Min Act: -0.1700
Data Index: 3586037 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2406. Min Act: -0.1700
Data Index: 7417415 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2249. Min Act: -0.1700
Data Index: 545602 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2406. Min Act: -0.1700
Data Index: 7544728 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2249. Min Act: -0.1700
Data Index: 6823640 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6776780 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.2406. Min Act: -0.1700
Data Index: 6849439 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.1935. Min Act: -0.1700
Data Index: 253761 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.1777. Min Act: -0.1700
Data Index: 4582954 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.1777. Min Act: -0.1700
Data Index: 3508560 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4603. Min Range: -3.4603
Max Act: 3.1777. Min Act: -0.1700
Data Index: 1383158 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19