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

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

Neuron 688 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0210. Min Act: -0.0000

Data Index: 67850 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1077224 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9377. Min Act: -0.0000

Data Index: 943669 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1207124 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8576. Min Act: -0.0000

Data Index: 1122806 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0089. Min Act: -0.0000

Data Index: 1252993 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9222. Min Act: -0.0000

Data Index: 764370 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9669. Min Act: -0.0000

Data Index: 53744 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1195483 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8467. Min Act: -0.0000

Data Index: 7077 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1159465 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9464. Min Act: -0.0000

Data Index: 954672 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9579. Min Act: -0.0000

Data Index: 698943 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8681. Min Act: -0.0000

Data Index: 551839 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1214807 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8736. Min Act: -0.0000

Data Index: 930136 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1096239 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8500. Min Act: -0.0000

Data Index: 448085 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8295. Min Act: -0.0000

Data Index: 501753 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.8176. Min Act: 0.0000

Data Index: 1272807 (C4 (Web Text))

Max Activating Token Index: 844