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

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

Neuron 3884 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: 0.7263. Min Range: -0.7263

Max Act: 0.7263. Min Act: -0.0000

Data Index: 244556 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1087154 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5912. Min Act: -0.0000

Data Index: 767935 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1115397 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.5369. Min Act: -0.0000

Data Index: 17560 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4972. Min Act: -0.0000

Data Index: 761665 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1137720 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4465. Min Act: -0.0000

Data Index: 196671 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4595. Min Act: -0.0000

Data Index: 515386 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1089384 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4128. Min Act: -0.0000

Data Index: 417515 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3936. Min Act: -0.0000

Data Index: 528146 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3911. Min Act: -0.0000

Data Index: 925134 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3881. Min Act: -0.0000

Data Index: 984613 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4118. Min Act: -0.0000

Data Index: 606419 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1224480 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3529. Min Act: -0.0000

Data Index: 18140 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3290. Min Act: -0.0000

Data Index: 132269 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3550. Min Act: -0.0000

Data Index: 72188 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.7263. Min Range: -0.7263

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1201623 (C4 (Web Text))

Max Activating Token Index: 478