Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.3112. Min Act: -0.1700
Data Index: 3826232 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2947. Min Act: -0.1700
Data Index: 8316401 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2617. Min Act: -0.1700
Data Index: 2887608 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2617. Min Act: -0.1700
Data Index: 7307787 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2782. Min Act: -0.1700
Data Index: 5105468 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2452. Min Act: -0.1700
Data Index: 3108107 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2452. Min Act: -0.1700
Data Index: 5546284 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2452. Min Act: -0.1700
Data Index: 5037727 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2287. Min Act: -0.1700
Data Index: 2304578 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2287. Min Act: -0.1699
Data Index: 3604369 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2121. Min Act: -0.1700
Data Index: 160971 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2121. Min Act: -0.1700
Data Index: 4833793 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2121. Min Act: -0.1700
Data Index: 6676748 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.2121. Min Act: -0.1700
Data Index: 6398434 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.1789. Min Act: -0.1700
Data Index: 7636529 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.1955. Min Act: -0.1700
Data Index: 8616462 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.1789. Min Act: -0.1700
Data Index: 7619631 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.1789. Min Act: -0.1700
Data Index: 3346802 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.1955. Min Act: -0.1700
Data Index: 8078748 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3112. Min Range: -2.3112
Max Act: 2.1789. Min Act: -0.1700
Data Index: 2173087 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19