Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1627 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.0512. Min Range: -6.0512
Max Act: 6.0512. Min Act: -0.0001
Data Index: 945559 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0512. Min Range: -6.0512
Max Act: 5.6278. Min Act: -0.0001
Data Index: 95888 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0512. Min Range: -6.0512
Max Act: 5.4633. Min Act: -0.0001
Data Index: 435713 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0512. Min Range: -6.0512
Max Act: 4.4198. Min Act: -0.0001
Data Index: 533371 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.8261. Min Act: -0.0001
Data Index: 167997 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.8210. Min Act: -0.0001
Data Index: 151979 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.2587. Min Act: -0.0001
Data Index: 116303 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.3437. Min Act: -0.0001
Data Index: 443124 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.0799. Min Act: -0.0001
Data Index: 525748 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.1852. Min Act: -0.0001
Data Index: 3168 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.9728. Min Act: -0.0001
Data Index: 314201 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.0763. Min Act: -0.0001
Data Index: 1012003 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.9197. Min Act: -0.0001
Data Index: 553976 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0512. Min Range: -6.0512
Max Act: 3.0618. Min Act: -0.0001
Data Index: 1040859 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.9934. Min Act: -0.0001
Data Index: 1323891 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.9502. Min Act: -0.0001
Data Index: 1162799 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.9470. Min Act: -0.0001
Data Index: 501578 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.7993. Min Act: -0.0001
Data Index: 1195085 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.8547. Min Act: -0.0001
Data Index: 994997 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0512. Min Range: -6.0512
Max Act: 2.7918. Min Act: -0.0001
Data Index: 1098836 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19