Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5309 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.9231. Min Act: -0.1700
Data Index: 3291961 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.9231. Min Act: -0.1700
Data Index: 1386412 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8918. Min Act: -0.1700
Data Index: 5655685 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8918. Min Act: -0.1700
Data Index: 4723986 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8918. Min Act: -0.1700
Data Index: 1459214 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 4951672 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 2973827 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 2610775 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 4590682 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 270430 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 4422365 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 4281990 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 4111234 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 2451856 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 32905 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 3523814 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 31072 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 1806819 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 1797649 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9231. Min Range: -3.9231
Max Act: 3.8606. Min Act: -0.1700
Data Index: 1766363 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19