Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.2326. Min Act: -0.0000

Data Index: 80282 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1079392 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.2671. Min Act: -0.0000

Data Index: 520809 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1566. Min Act: -0.0000

Data Index: 211325 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.2367. Min Act: -0.0001

Data Index: 440697 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.2296. Min Act: -0.0000

Data Index: 251992 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1999. Min Act: -0.0000

Data Index: 168850 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0853. Min Act: -0.0000

Data Index: 384161 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1990. Min Act: -0.0001

Data Index: 89809 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1993. Min Act: -0.0000

Data Index: 613907 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1409. Min Act: -0.0000

Data Index: 830141 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1241. Min Act: -0.0001

Data Index: 192144 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0982. Min Act: -0.0001

Data Index: 99051 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1144. Min Act: -0.0001

Data Index: 97790 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1041. Min Act: -0.0001

Data Index: 1289739 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9697. Min Act: -0.0001

Data Index: 710660 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0859. Min Act: -0.0000

Data Index: 720753 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0866. Min Act: -0.0000

Data Index: 410983 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1204. Min Act: -0.0001

Data Index: 1120073 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0917. Min Act: -0.0000

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 39