Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2815 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2810. Min Range: -2.2810
Max Act: 2.2810. Min Act: -0.0001
Data Index: 715304 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2810. Min Range: -2.2810
Max Act: 2.2492. Min Act: -0.0001
Data Index: 1159494 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2810. Min Range: -2.2810
Max Act: 2.1746. Min Act: -0.0001
Data Index: 74983 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2810. Min Range: -2.2810
Max Act: 2.0967. Min Act: -0.0001
Data Index: 1332640 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.9852. Min Act: -0.0001
Data Index: 925450 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2810. Min Range: -2.2810
Max Act: 2.2228. Min Act: -0.0001
Data Index: 810331 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.8304. Min Act: -0.0001
Data Index: 927149 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.7117. Min Act: -0.0001
Data Index: 682749 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.6951. Min Act: -0.0001
Data Index: 690616 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.7724. Min Act: -0.0001
Data Index: 353693 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.7375. Min Act: -0.0001
Data Index: 928247 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.7646. Min Act: -0.0001
Data Index: 749228 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.5600. Min Act: -0.0001
Data Index: 503965 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.6561. Min Act: -0.0001
Data Index: 707869 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.5753. Min Act: -0.0001
Data Index: 646101 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.6260. Min Act: -0.0001
Data Index: 1194621 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.5401. Min Act: -0.0001
Data Index: 1321978 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.6211. Min Act: -0.0001
Data Index: 875967 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.5013. Min Act: -0.0001
Data Index: 531168 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2810. Min Range: -2.2810
Max Act: 1.6015. Min Act: -0.0001
Data Index: 1261390 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19