Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3559 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.1418. Min Act: -0.0000

Data Index: 742684 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.0686. Min Act: -0.0000

Data Index: 520032 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.0270. Min Act: -0.0000

Data Index: 761660 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9285. Min Act: -0.0000

Data Index: 274338 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9697. Min Act: -0.0000

Data Index: 129424 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9356. Min Act: -0.0000

Data Index: 929233 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8277. Min Act: -0.0000

Data Index: 291618 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8242. Min Act: -0.0000

Data Index: 314246 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8358. Min Act: -0.0000

Data Index: 904338 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8179. Min Act: -0.0000

Data Index: 77654 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7658. Min Act: -0.0000

Data Index: 288017 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8048. Min Act: -0.0000

Data Index: 785372 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8055. Min Act: -0.0000

Data Index: 155391 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8026. Min Act: -0.0000

Data Index: 847648 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7805. Min Act: -0.0000

Data Index: 692029 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7641. Min Act: -0.0000

Data Index: 838254 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7696. Min Act: -0.0000

Data Index: 963486 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7128. Min Act: -0.0000

Data Index: 149517 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7622. Min Act: -0.0000

Data Index: 575789 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.7573. Min Act: -0.0000

Data Index: 849354 (C4 (Web Text))

Max Activating Token Index: 532