Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 881 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2737. Min Act: -0.1700
Data Index: 1778961 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2406. Min Act: -0.1700
Data Index: 3209903 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2075. Min Act: -0.1700
Data Index: 7581418 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2075. Min Act: -0.1700
Data Index: 3187983 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2075. Min Act: -0.1700
Data Index: 4955236 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2075. Min Act: -0.1700
Data Index: 6445535 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2075. Min Act: -0.1700
Data Index: 8495939 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2241. Min Act: -0.1700
Data Index: 6566314 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1698
Data Index: 6658116 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.2241. Min Act: -0.1700
Data Index: 1245951 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1700
Data Index: 6864200 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1700
Data Index: 5864575 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1700
Data Index: 1824962 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1700
Data Index: 7772162 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1700
Data Index: 5877238 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1743. Min Act: -0.1700
Data Index: 190992 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1743. Min Act: -0.1700
Data Index: 5720124 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1743. Min Act: -0.1700
Data Index: 6864199 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1743. Min Act: -0.1700
Data Index: 4116013 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2737. Min Range: -2.2737
Max Act: 2.1909. Min Act: -0.1700
Data Index: 4181917 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19