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

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

Neuron 3036 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: 2.7691. Min Range: -2.7691

Max Act: 2.7552. Min Act: -0.0000

Data Index: 1172758 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.7691. Min Act: -0.0000

Data Index: 1039666 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.6296. Min Act: -0.0000

Data Index: 808899 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.6890. Min Act: -0.0000

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.4391. Min Act: -0.0000

Data Index: 447150 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.2965. Min Act: -0.0000

Data Index: 652291 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1015102 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.4776. Min Act: -0.0000

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.2268. Min Act: -0.0000

Data Index: 754188 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.2102. Min Act: -0.0000

Data Index: 1240310 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.2327. Min Act: -0.0000

Data Index: 51836 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.1778. Min Act: -0.0000

Data Index: 640059 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.3167. Min Act: -0.0000

Data Index: 983658 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.2914. Min Act: -0.0000

Data Index: 1117325 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1066114 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.1150. Min Act: -0.0000

Data Index: 604117 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.3565. Min Act: -0.0000

Data Index: 1265440 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.0455. Min Act: -0.0000

Data Index: 1019122 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.1354. Min Act: -0.0000

Data Index: 791856 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 2.7691. Min Range: -2.7691

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1198324 (C4 (Web Text))

Max Activating Token Index: 90