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

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

Neuron 766 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4560. Min Act: -0.0000

Data Index: 260175 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4197. Min Act: -0.0000

Data Index: 559518 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4031. Min Act: -0.0000

Data Index: 871598 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4016. Min Act: -0.0000

Data Index: 205629 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.4150. Min Act: -0.0000

Data Index: 838412 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3955. Min Act: -0.0000

Data Index: 354315 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1336337 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3737. Min Act: -0.0000

Data Index: 280765 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3867. Min Act: -0.0000

Data Index: 420049 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3834. Min Act: -0.0001

Data Index: 1323873 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1105887 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3703. Min Act: -0.0000

Data Index: 362653 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3607. Min Act: -0.0000

Data Index: 405584 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3495. Min Act: -0.0000

Data Index: 441270 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3588. Min Act: -0.0000

Data Index: 1010608 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3587. Min Act: -0.0000

Data Index: 521846 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1007314 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3395. Min Act: -0.0000

Data Index: 722769 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3270. Min Act: -0.0000

Data Index: 454848 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.4560. Min Range: -0.4560

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1110076 (C4 (Web Text))

Max Activating Token Index: 947