Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.4244. Min Act: -0.1700
Data Index: 79104 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.4244. Min Act: -0.1700
Data Index: 8107579 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2994. Min Act: -0.1700
Data Index: 6149943 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2681. Min Act: -0.1700
Data Index: 6772859 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2681. Min Act: -0.1700
Data Index: 2038001 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2681. Min Act: -0.1700
Data Index: 2715921 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2681. Min Act: -0.1700
Data Index: 6534701 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2369. Min Act: -0.1700
Data Index: 5935294 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2369. Min Act: -0.1700
Data Index: 1272146 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2056. Min Act: -0.1700
Data Index: 7222159 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2369. Min Act: -0.1700
Data Index: 7634448 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2056. Min Act: -0.1700
Data Index: 8345882 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2056. Min Act: -0.1700
Data Index: 79110 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2056. Min Act: -0.1700
Data Index: 727318 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.1744. Min Act: -0.1700
Data Index: 1892681 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2056. Min Act: -0.1700
Data Index: 888892 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.1744. Min Act: -0.1700
Data Index: 1012227 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.1744. Min Act: -0.1700
Data Index: 389899 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.2056. Min Act: -0.1700
Data Index: 1647918 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4244. Min Range: -4.4244
Max Act: 4.1744. Min Act: -0.1700
Data Index: 7693956 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19