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

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

Neuron 3545 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.7911. Min Act: -0.0001

Data Index: 1163631 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.7258. Min Act: -0.0000

Data Index: 388626 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5552. Min Act: -0.0001

Data Index: 1231162 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6061. Min Act: -0.0001

Data Index: 811241 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6206. Min Act: -0.0001

Data Index: 1012562 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6355. Min Act: -0.0001

Data Index: 997233 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5683. Min Act: -0.0001

Data Index: 374678 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6564. Min Act: -0.0001

Data Index: 1389962 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1539361 (Python Code)

Max Activating Token Index: 288

Text #9

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6281. Min Act: -0.0001

Data Index: 46475 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6478. Min Act: -0.0001

Data Index: 367521 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5879. Min Act: -0.0001

Data Index: 1464148 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5915. Min Act: -0.0001

Data Index: 870070 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6264. Min Act: -0.0001

Data Index: 1611618 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6137. Min Act: -0.0001

Data Index: 134409 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5710. Min Act: -0.0001

Data Index: 883475 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5731. Min Act: -0.0001

Data Index: 1499331 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6004. Min Act: -0.0001

Data Index: 1401729 (Python Code)

Max Activating Token Index: 80

Text #18

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.5245. Min Act: -0.0001

Data Index: 1017164 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.7911. Min Range: -0.7911

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1323890 (C4 (Web Text))

Max Activating Token Index: 692