Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 862 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1349893 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.2355. Min Act: -0.0000

Data Index: 359592 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.2106. Min Act: -0.0000

Data Index: 734771 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.1470. Min Act: -0.0000

Data Index: 351666 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1081688 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0399. Min Act: -0.0000

Data Index: 921868 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0940. Min Act: -0.0000

Data Index: 988823 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.1312. Min Act: -0.0000

Data Index: 659635 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0525. Min Act: -0.0000

Data Index: 815530 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0150. Min Act: -0.0000

Data Index: 244142 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0171. Min Act: -0.0000

Data Index: 1202759 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1245209 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.2355. Min Range: -1.2355

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1208318 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1115302 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.9091. Min Act: -0.0000

Data Index: 420966 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.9228. Min Act: -0.0000

Data Index: 262251 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1042895 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.9191. Min Act: -0.0000

Data Index: 530617 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.8934. Min Act: -0.0000

Data Index: 240966 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.2355. Min Range: -1.2355

Max Act: 0.9131. Min Act: -0.0000

Data Index: 105055 (C4 (Web Text))

Max Activating Token Index: 925