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

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

Neuron 3626 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.5153. Min Act: -0.0001

Data Index: 339961 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.6946. Min Act: -0.0001

Data Index: 779923 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.6009. Min Act: -0.0001

Data Index: 934629 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.4734. Min Act: -0.0001

Data Index: 154050 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3785. Min Act: -0.0001

Data Index: 63898 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3905. Min Act: -0.0001

Data Index: 1243993 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3785. Min Act: -0.0001

Data Index: 816452 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.4193. Min Act: -0.0001

Data Index: 987770 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3963. Min Act: -0.0000

Data Index: 734128 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3600. Min Act: -0.0001

Data Index: 329499 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3044. Min Act: -0.0001

Data Index: 805939 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.1857. Min Act: -0.0001

Data Index: 835300 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.2998. Min Act: -0.0001

Data Index: 736024 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3253. Min Act: -0.0001

Data Index: 63380 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3525. Min Act: -0.0000

Data Index: 702863 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.4362. Min Act: -0.0001

Data Index: 1208268 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3754. Min Act: -0.0001

Data Index: 234166 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.2607. Min Act: -0.0001

Data Index: 39426 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.3034. Min Act: -0.0001

Data Index: 872422 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.6946. Min Range: -1.6946

Max Act: 1.2854. Min Act: -0.0001

Data Index: 1320001 (C4 (Web Text))

Max Activating Token Index: 867