Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2274 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1538. Min Range: -5.1538
Max Act: 5.1538. Min Act: -0.1700
Data Index: 4405148 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9975. Min Act: -0.1700
Data Index: 1052055 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9975. Min Act: -0.1700
Data Index: 3273072 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9663. Min Act: -0.1700
Data Index: 7116046 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9350. Min Act: -0.1700
Data Index: 2201688 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9350. Min Act: -0.1700
Data Index: 8055196 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9350. Min Act: -0.1700
Data Index: 7745606 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9663. Min Act: -0.1700
Data Index: 2450833 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9350. Min Act: -0.1700
Data Index: 3298829 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.9038. Min Act: -0.1700
Data Index: 7471560 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.8725. Min Act: -0.1700
Data Index: 6340456 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.8725. Min Act: -0.1700
Data Index: 969337 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.8413. Min Act: -0.1700
Data Index: 5574912 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.8413. Min Act: -0.1700
Data Index: 6526573 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.8100. Min Act: -0.1700
Data Index: 6089478 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.7788. Min Act: -0.1700
Data Index: 878780 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.8100. Min Act: -0.1700
Data Index: 6745220 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.7475. Min Act: -0.1700
Data Index: 2003975 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.7475. Min Act: -0.1700
Data Index: 2216516 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1538. Min Range: -5.1538
Max Act: 4.7163. Min Act: -0.1700
Data Index: 7026014 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19