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

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

Neuron 1645 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.6622. Min Act: -0.0000

Data Index: 740110 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.6533. Min Act: -0.0000

Data Index: 57397 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.9209. Min Act: -0.0000

Data Index: 450310 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3875. Min Act: -0.0000

Data Index: 1230350 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3285. Min Act: -0.0000

Data Index: 962732 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.4179. Min Act: -0.0000

Data Index: 103978 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3950. Min Act: -0.0000

Data Index: 870946 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1243427 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1001145 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2761. Min Act: -0.0000

Data Index: 995554 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3469. Min Act: -0.0000

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3384. Min Act: -0.0000

Data Index: 79438 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3459. Min Act: -0.0000

Data Index: 1338414 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2498. Min Act: -0.0000

Data Index: 1194261 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3489. Min Act: -0.0000

Data Index: 96876 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.3629. Min Act: -0.0000

Data Index: 815340 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2574. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2523. Min Act: -0.0000

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2717. Min Act: -0.0000

Data Index: 256567 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.9209. Min Range: -1.9209

Max Act: 1.2339. Min Act: -0.0000

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 630