Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1045 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.6356. Min Act: -0.0001

Data Index: 318982 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5255. Min Act: -0.0001

Data Index: 560086 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5431. Min Act: -0.0001

Data Index: 227151 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.5211. Min Act: -0.0001

Data Index: 875422 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4494. Min Act: -0.0001

Data Index: 1211841 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4744. Min Act: -0.0001

Data Index: 113732 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1331598 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4706. Min Act: -0.0001

Data Index: 1027740 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4225. Min Act: -0.0001

Data Index: 217033 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4712. Min Act: -0.0001

Data Index: 424893 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4327. Min Act: -0.0001

Data Index: 60054 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4484. Min Act: -0.0001

Data Index: 488708 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1156614 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4729. Min Act: -0.0001

Data Index: 459676 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4097. Min Act: -0.0001

Data Index: 353555 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4387. Min Act: -0.0001

Data Index: 719420 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4202. Min Act: -0.0001

Data Index: 1042292 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4009. Min Act: -0.0001

Data Index: 4924 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4370. Min Act: -0.0001

Data Index: 850727 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.6356. Min Range: -0.6356

Max Act: 0.4497. Min Act: -0.0001

Data Index: 812946 (C4 (Web Text))

Max Activating Token Index: 31