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

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

Neuron 5050 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: 0.9941. Min Range: -0.9941

Max Act: 0.9941. Min Act: 0.0000

Data Index: 767243 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1324285 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1008427 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8553. Min Act: -0.0000

Data Index: 580905 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1135462 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8206. Min Act: -0.0000

Data Index: 375204 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8175. Min Act: -0.0000

Data Index: 750197 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8356. Min Act: -0.0000

Data Index: 455516 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8067. Min Act: -0.0000

Data Index: 588171 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8242. Min Act: 0.0000

Data Index: 605008 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7949. Min Act: 0.0001

Data Index: 1033549 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1090870 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7965. Min Act: -0.0000

Data Index: 600601 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7894. Min Act: -0.0000

Data Index: 200005 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7910. Min Act: -0.0000

Data Index: 532442 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7878. Min Act: -0.0000

Data Index: 933611 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8152. Min Act: 0.0000

Data Index: 184690 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7809. Min Act: -0.0000

Data Index: 813816 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1047645 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1180607 (C4 (Web Text))

Max Activating Token Index: 469