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

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

Neuron 1835 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0072. Min Range: -1.0072

Max Act: 1.0072. Min Act: -0.0002

Data Index: 481516 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8788. Min Act: -0.0002

Data Index: 1026840 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8960. Min Act: -0.0002

Data Index: 835205 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8439. Min Act: -0.0002

Data Index: 66601 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8770. Min Act: -0.0002

Data Index: 500714 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8074. Min Act: -0.0002

Data Index: 527502 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8326. Min Act: -0.0002

Data Index: 234190 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7585. Min Act: -0.0002

Data Index: 932823 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7366. Min Act: -0.0002

Data Index: 983101 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7571. Min Act: -0.0002

Data Index: 1010718 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7023. Min Act: -0.0002

Data Index: 1251077 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7320. Min Act: -0.0002

Data Index: 872089 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7208. Min Act: -0.0002

Data Index: 591354 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7624. Min Act: -0.0002

Data Index: 1249269 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6335. Min Act: -0.0002

Data Index: 388810 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6637. Min Act: -0.0002

Data Index: 961234 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7026. Min Act: -0.0002

Data Index: 334380 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6576. Min Act: -0.0002

Data Index: 380045 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6799. Min Act: -0.0002

Data Index: 570278 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6803. Min Act: -0.0002

Data Index: 1191985 (C4 (Web Text))

Max Activating Token Index: 709