Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4438 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.7010. Min Act: -0.0001
Data Index: 671292 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.7714. Min Act: -0.0001
Data Index: 906175 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.8559. Min Act: -0.0001
Data Index: 398485 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6413. Min Act: -0.0001
Data Index: 828004 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6942. Min Act: -0.0001
Data Index: 464838 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6914. Min Act: -0.0001
Data Index: 1075502 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6769. Min Act: -0.0001
Data Index: 502255 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.7198. Min Act: -0.0001
Data Index: 160423 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5553. Min Act: -0.0001
Data Index: 745195 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5342. Min Act: -0.0001
Data Index: 1327636 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6202. Min Act: -0.0001
Data Index: 700380 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5777. Min Act: -0.0001
Data Index: 722895 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5802. Min Act: -0.0001
Data Index: 26831 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5886. Min Act: -0.0001
Data Index: 1192365 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5782. Min Act: -0.0001
Data Index: 1252870 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5593. Min Act: -0.0001
Data Index: 524545 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5424. Min Act: -0.0001
Data Index: 1084135 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6343. Min Act: -0.0001
Data Index: 1075106 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.5314. Min Act: -0.0001
Data Index: 1046189 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8559. Min Range: -1.8559
Max Act: 1.6184. Min Act: -0.0001
Data Index: 341830 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19