Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.4202. Min Act: -0.1700
Data Index: 7556761 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 4163796 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.3577. Min Act: -0.1700
Data Index: 5264281 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2639. Min Act: -0.1700
Data Index: 7084687 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 5999462 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 4756121 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 4695594 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 3177829 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 4421873 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2633662 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 3025717 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2327. Min Act: -0.1700
Data Index: 5642691 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 7609875 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.2014. Min Act: -0.1700
Data Index: 2477237 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 1379576 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 4109449 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 6053384 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 1774390 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 5235322 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4202. Min Range: -5.4202
Max Act: 5.1702. Min Act: -0.1700
Data Index: 6918098 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19