Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3812 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.3089. Min Range: -4.3089
Max Act: 4.3089. Min Act: -0.0001
Data Index: 758145 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3089. Min Range: -4.3089
Max Act: 4.1619. Min Act: -0.0001
Data Index: 399178 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3089. Min Range: -4.3089
Max Act: 4.1743. Min Act: -0.0001
Data Index: 1196709 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.2471. Min Act: -0.0001
Data Index: 276153 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.4562. Min Act: -0.0001
Data Index: 118103 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.4660. Min Act: -0.0001
Data Index: 431155 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.5727. Min Act: -0.0001
Data Index: 1347029 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.3814. Min Act: -0.0001
Data Index: 85109 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.3289. Min Act: -0.0001
Data Index: 761372 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.6769. Min Act: -0.0001
Data Index: 1215571 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.3403. Min Act: -0.0001
Data Index: 1172056 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.0664. Min Act: -0.0001
Data Index: 829912 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.4029. Min Act: -0.0001
Data Index: 935735 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.4492. Min Act: -0.0001
Data Index: 1346808 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.2521. Min Act: -0.0001
Data Index: 1208252 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.2240. Min Act: -0.0001
Data Index: 267071 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.1803. Min Act: -0.0001
Data Index: 1112425 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.4646. Min Act: -0.0001
Data Index: 951922 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.3143. Min Act: -0.0001
Data Index: 729182 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3089. Min Range: -4.3089
Max Act: 3.5943. Min Act: -0.0001
Data Index: 1298427 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19