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

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

Neuron 2943 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2358. Min Range: -3.2358

Max Act: 3.2358. Min Act: -0.0001

Data Index: 509938 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.9928. Min Act: -0.0001

Data Index: 900253 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.9898. Min Act: -0.0001

Data Index: 1015102 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 3.2358. Min Range: -3.2358

Max Act: 3.0025. Min Act: -0.0001

Data Index: 888093 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.9304. Min Act: -0.0001

Data Index: 374577 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.7729. Min Act: -0.0001

Data Index: 903461 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.8951. Min Act: -0.0001

Data Index: 869149 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.8941. Min Act: -0.0001

Data Index: 1059036 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.8368. Min Act: -0.0000

Data Index: 498959 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.8332. Min Act: -0.0001

Data Index: 11334 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.6139. Min Act: -0.0001

Data Index: 86476 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.7530. Min Act: -0.0000

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.7550. Min Act: -0.0001

Data Index: 813818 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.7438. Min Act: -0.0001

Data Index: 1114536 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.7261. Min Act: -0.0001

Data Index: 897666 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.8301. Min Act: -0.0001

Data Index: 584853 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.7073. Min Act: -0.0001

Data Index: 115134 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.6946. Min Act: -0.0001

Data Index: 835082 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.4050. Min Act: -0.0001

Data Index: 926262 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 3.2358. Min Range: -3.2358

Max Act: 2.3860. Min Act: -0.0000

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 206