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

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

Neuron 241 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.8072. Min Act: -0.0001

Data Index: 240846 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7415. Min Act: -0.0001

Data Index: 1148571 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.7100. Min Act: -0.0001

Data Index: 1263935 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6588. Min Act: -0.0001

Data Index: 209058 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6409. Min Act: -0.0001

Data Index: 888956 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1346016 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5151. Min Act: -0.0001

Data Index: 69975 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5387. Min Act: -0.0001

Data Index: 754259 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5315. Min Act: -0.0001

Data Index: 1039838 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5103. Min Act: -0.0001

Data Index: 637424 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5344. Min Act: -0.0001

Data Index: 937249 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5017. Min Act: -0.0001

Data Index: 281334 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5012. Min Act: -0.0001

Data Index: 932909 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5190. Min Act: -0.0001

Data Index: 1315579 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4564. Min Act: -0.0001

Data Index: 299876 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4916. Min Act: -0.0001

Data Index: 658621 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.5026. Min Act: -0.0001

Data Index: 930412 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4828. Min Act: -0.0001

Data Index: 362547 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4763. Min Act: -0.0001

Data Index: 646864 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.8072. Min Range: -0.8072

Max Act: 0.4740. Min Act: -0.0001

Data Index: 823879 (C4 (Web Text))

Max Activating Token Index: 506