Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2745 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.2526. Min Act: -0.0001
Data Index: 1464354 (Python Code)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.0831. Min Act: -0.0001
Data Index: 1551456 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.1683. Min Act: -0.0001
Data Index: 1384737 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.2359. Min Act: -0.0001
Data Index: 1566057 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.2402. Min Act: -0.0001
Data Index: 1148586 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.2167. Min Act: -0.0001
Data Index: 1533628 (Python Code)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2526. Min Range: -2.2526
Max Act: 2.1045. Min Act: -0.0001
Data Index: 1500109 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.7296. Min Act: -0.0001
Data Index: 574457 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.9115. Min Act: -0.0001
Data Index: 1590331 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.8813. Min Act: -0.0001
Data Index: 1240166 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.8264. Min Act: -0.0001
Data Index: 783029 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.7733. Min Act: -0.0001
Data Index: 662064 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.7666. Min Act: -0.0001
Data Index: 1048415 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.6699. Min Act: -0.0001
Data Index: 418535 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.6623. Min Act: -0.0001
Data Index: 1052563 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.9046. Min Act: -0.0001
Data Index: 507437 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.7118. Min Act: -0.0001
Data Index: 903233 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.8465. Min Act: -0.0001
Data Index: 324659 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.6727. Min Act: -0.0001
Data Index: 1008918 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2526. Min Range: -2.2526
Max Act: 1.7587. Min Act: -0.0001
Data Index: 1010902 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19