Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2252 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.8297. Min Act: -0.0001

Data Index: 449210 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.6157. Min Act: -0.0001

Data Index: 28199 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5852. Min Act: -0.0001

Data Index: 821442 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5930. Min Act: -0.0001

Data Index: 123278 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5718. Min Act: -0.0001

Data Index: 406477 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5592. Min Act: -0.0001

Data Index: 806159 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5215. Min Act: -0.0001

Data Index: 1203569 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5294. Min Act: -0.0001

Data Index: 125014 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5457. Min Act: -0.0001

Data Index: 691374 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4803. Min Act: -0.0001

Data Index: 251216 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.5322. Min Act: -0.0001

Data Index: 483430 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4904. Min Act: -0.0001

Data Index: 76658 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4994. Min Act: -0.0001

Data Index: 680179 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4988. Min Act: -0.0001

Data Index: 291596 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1333557 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4646. Min Act: -0.0001

Data Index: 888550 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1186089 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4242. Min Act: -0.0001

Data Index: 913337 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4119. Min Act: -0.0001

Data Index: 691197 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.8297. Min Range: -0.8297

Max Act: 0.4521. Min Act: -0.0001

Data Index: 1333409 (C4 (Web Text))

Max Activating Token Index: 469