Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.3569. Min Act: -0.1700
Data Index: 647176 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.3257. Min Act: -0.1700
Data Index: 6266230 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.2319. Min Act: -0.1700
Data Index: 2276343 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.1381. Min Act: -0.1700
Data Index: 5074008 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.1069. Min Act: -0.1700
Data Index: 8298853 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.0756. Min Act: -0.1700
Data Index: 4272799 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.1069. Min Act: -0.1700
Data Index: 1570915 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.0756. Min Act: -0.1700
Data Index: 5745509 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.0444. Min Act: -0.1700
Data Index: 5858790 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.0287. Min Act: -0.1700
Data Index: 3019744 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9818. Min Act: -0.1700
Data Index: 114400 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3569. Min Range: -4.3569
Max Act: 4.0131. Min Act: -0.1700
Data Index: 1115385 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9975. Min Act: -0.1700
Data Index: 6091258 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9975. Min Act: -0.1700
Data Index: 2848172 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9662. Min Act: -0.1700
Data Index: 7833229 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9506. Min Act: -0.1700
Data Index: 4677973 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9506. Min Act: -0.1700
Data Index: 1522658 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9350. Min Act: -0.1700
Data Index: 4717219 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9662. Min Act: -0.1700
Data Index: 3603114 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3569. Min Range: -4.3569
Max Act: 3.9350. Min Act: -0.1700
Data Index: 55838 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19