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

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

Neuron 3028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.9316. Min Act: -0.0000

Data Index: 520193 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5504. Min Act: -0.0000

Data Index: 1076368 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1237034 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4779. Min Act: -0.0000

Data Index: 619767 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5015. Min Act: -0.0000

Data Index: 345660 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5308. Min Act: -0.0000

Data Index: 764488 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5184. Min Act: -0.0000

Data Index: 542672 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5446. Min Act: -0.0000

Data Index: 947853 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4464. Min Act: -0.0000

Data Index: 1173570 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4838. Min Act: -0.0000

Data Index: 768679 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5700. Min Act: -0.0000

Data Index: 155006 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.3513. Min Act: -0.0000

Data Index: 750516 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5189. Min Act: -0.0000

Data Index: 1041770 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4305. Min Act: -0.0000

Data Index: 119199 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4756. Min Act: -0.0000

Data Index: 244041 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1249366 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4723. Min Act: -0.0000

Data Index: 318059 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.5379. Min Act: -0.0000

Data Index: 155993 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.4738. Min Act: -0.0000

Data Index: 835891 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.9316. Min Range: -1.9316

Max Act: 1.3458. Min Act: -0.0000

Data Index: 1046719 (C4 (Web Text))

Max Activating Token Index: 345