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

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

Neuron 26 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.6944. Min Act: -0.0000

Data Index: 249321 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1105134 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.5331. Min Act: -0.0000

Data Index: 717757 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.4288. Min Act: -0.0000

Data Index: 54578 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.4100. Min Act: -0.0000

Data Index: 188412 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.3924. Min Act: -0.0000

Data Index: 412988 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.4393. Min Act: -0.0000

Data Index: 467192 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1036377 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.3105. Min Act: -0.0000

Data Index: 124617 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.3810. Min Act: -0.0000

Data Index: 352056 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.2758. Min Act: -0.0000

Data Index: 157065 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.2753. Min Act: -0.0000

Data Index: 1224791 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1040433 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.2413. Min Act: -0.0000

Data Index: 1039031 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.2224. Min Act: -0.0000

Data Index: 149546 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.1500. Min Act: -0.0000

Data Index: 97454 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.1217. Min Act: -0.0000

Data Index: 894145 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.2328. Min Act: -0.0000

Data Index: 786099 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1197662 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.6944. Min Range: -1.6944

Max Act: 1.0755. Min Act: -0.0000

Data Index: 148431 (C4 (Web Text))

Max Activating Token Index: 563