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

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

Neuron 1990 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0002

Data Index: 255454 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4706. Min Act: -0.0001

Data Index: 101910 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4934. Min Act: -0.0002

Data Index: 38943 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4829. Min Act: -0.0001

Data Index: 781740 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4438. Min Act: -0.0002

Data Index: 1148978 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4297. Min Act: -0.0002

Data Index: 878916 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4315. Min Act: -0.0002

Data Index: 1065723 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4295. Min Act: -0.0001

Data Index: 1209436 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4400. Min Act: -0.0001

Data Index: 496806 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4344. Min Act: -0.0002

Data Index: 1074864 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4335. Min Act: -0.0001

Data Index: 358871 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4719. Min Act: -0.0002

Data Index: 545462 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4443. Min Act: -0.0001

Data Index: 907998 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1259569 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4658. Min Act: -0.0002

Data Index: 1304990 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4039. Min Act: -0.0002

Data Index: 1105557 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4325. Min Act: -0.0001

Data Index: 751580 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4419. Min Act: -0.0002

Data Index: 1066760 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4034. Min Act: -0.0002

Data Index: 677831 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4142. Min Act: -0.0002

Data Index: 911190 (C4 (Web Text))

Max Activating Token Index: 189