Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3848. Min Act: -0.1700
Data Index: 3991404 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3535. Min Act: -0.1700
Data Index: 4624126 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3064. Min Act: -0.1700
Data Index: 3563804 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3378. Min Act: -0.1700
Data Index: 5408859 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3378. Min Act: -0.1700
Data Index: 7840962 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3064. Min Act: -0.1700
Data Index: 6859845 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3221. Min Act: -0.1700
Data Index: 8701407 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2436. Min Act: -0.1700
Data Index: 7224713 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2593. Min Act: -0.1700
Data Index: 53144 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2750. Min Act: -0.1700
Data Index: 271475 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3064. Min Act: -0.1700
Data Index: 5014935 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.3064. Min Act: -0.1700
Data Index: 3222043 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2593. Min Act: -0.1700
Data Index: 5730714 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2593. Min Act: -0.1700
Data Index: 2359646 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2593. Min Act: -0.1700
Data Index: 188946 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2750. Min Act: -0.1700
Data Index: 4797554 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2593. Min Act: -0.1700
Data Index: 5240211 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2750. Min Act: -0.1700
Data Index: 5655277 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2436. Min Act: -0.1700
Data Index: 7444843 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3848. Min Range: -3.3848
Max Act: 3.2593. Min Act: -0.1700
Data Index: 5169210 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19