Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2566. Min Act: -0.1700
Data Index: 505553 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2390. Min Act: -0.1688
Data Index: 3728711 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2302. Min Act: -0.1699
Data Index: 4349670 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2302. Min Act: -0.1672
Data Index: 1354431 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2390. Min Act: -0.1700
Data Index: 4887244 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2213. Min Act: -0.1697
Data Index: 7463010 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2213. Min Act: -0.1700
Data Index: 7482982 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2302. Min Act: -0.1698
Data Index: 7490810 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2302. Min Act: -0.1697
Data Index: 393935 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2125. Min Act: -0.1696
Data Index: 2001700 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2213. Min Act: -0.1700
Data Index: 6072519 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2213. Min Act: -0.1700
Data Index: 733378 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2125. Min Act: -0.1698
Data Index: 4402413 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2213. Min Act: -0.1700
Data Index: 2743645 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2125. Min Act: -0.1700
Data Index: 375775 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2037. Min Act: -0.1700
Data Index: 4450389 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2125. Min Act: -0.1699
Data Index: 138883 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2125. Min Act: -0.1700
Data Index: 3815653 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2125. Min Act: -0.1697
Data Index: 8383928 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2566. Min Range: -1.2566
Max Act: 1.2037. Min Act: -0.1700
Data Index: 3457418 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19