Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.2849. Min Act: -0.1700
Data Index: 7122548 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.2224. Min Act: -0.1700
Data Index: 2241714 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.2224. Min Act: -0.1700
Data Index: 5073445 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1911. Min Act: -0.1700
Data Index: 4355392 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1911. Min Act: -0.1700
Data Index: 5800460 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1911. Min Act: -0.1700
Data Index: 6460416 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1911. Min Act: -0.1700
Data Index: 892647 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1911. Min Act: -0.1700
Data Index: 7939766 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1599. Min Act: -0.1700
Data Index: 2682425 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 7190640 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1599. Min Act: -0.1700
Data Index: 8619909 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1599. Min Act: -0.1700
Data Index: 4176539 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 2167339 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.0974. Min Act: -0.1700
Data Index: 1987270 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 3826038 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 3621740 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 8433424 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 8445407 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 1715334 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2849. Min Range: -5.2849
Max Act: 5.1286. Min Act: -0.1700
Data Index: 4815635 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19