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

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

Neuron 4010 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: 0.5176. Min Range: -0.5176

Max Act: 0.5176. Min Act: -0.0000

Data Index: 622145 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4379. Min Act: -0.0000

Data Index: 364322 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4225. Min Act: -0.0000

Data Index: 494632 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4664. Min Act: -0.0000

Data Index: 764321 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1099240 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1055555 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4283. Min Act: -0.0000

Data Index: 475703 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3760. Min Act: -0.0000

Data Index: 91436 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1224271 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3838. Min Act: -0.0000

Data Index: 77936 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3588. Min Act: -0.0000

Data Index: 793778 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3775. Min Act: -0.0000

Data Index: 201536 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1391429 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3423. Min Act: -0.0000

Data Index: 414568 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3490. Min Act: -0.0000

Data Index: 590070 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3374. Min Act: -0.0000

Data Index: 99728 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1394996 (Python Code)

Max Activating Token Index: 719

Text #17

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3567. Min Act: -0.0000

Data Index: 161836 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3093. Min Act: -0.0000

Data Index: 230501 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1273986 (C4 (Web Text))

Max Activating Token Index: 793