Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.5483. Min Act: -0.1700
Data Index: 5784827 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.5170. Min Act: -0.1700
Data Index: 4954038 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.4233. Min Act: -0.1699
Data Index: 6500351 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.4233. Min Act: -0.1700
Data Index: 3627133 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.4233. Min Act: -0.1700
Data Index: 8393633 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.4233. Min Act: -0.1700
Data Index: 2281655 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.4233. Min Act: -0.1700
Data Index: 1341932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3920. Min Act: -0.1700
Data Index: 5051730 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3920. Min Act: -0.1699
Data Index: 1358420 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3920. Min Act: -0.1700
Data Index: 145104 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3920. Min Act: -0.1700
Data Index: 4392369 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3920. Min Act: -0.1700
Data Index: 4325869 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3920. Min Act: -0.1700
Data Index: 7685791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 2403320 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 1581521 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 4718020 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 2271990 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 5260772 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 1878824 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5483. Min Range: -4.5483
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6056682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19