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

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

Neuron 1953 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: 2.2282. Min Range: -2.2282

Max Act: 2.2282. Min Act: -0.0000

Data Index: 835927 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.9059. Min Act: -0.0000

Data Index: 1159735 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.8220. Min Act: -0.0000

Data Index: 198927 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.8596. Min Act: -0.0000

Data Index: 541761 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.9727. Min Act: -0.0000

Data Index: 6442 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.7310. Min Act: -0.0000

Data Index: 915225 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.5118. Min Act: -0.0000

Data Index: 971437 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.6605. Min Act: -0.0000

Data Index: 507852 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.6209. Min Act: -0.0000

Data Index: 1216106 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.5024. Min Act: -0.0000

Data Index: 304917 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.6882. Min Act: -0.0000

Data Index: 1089524 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.4727. Min Act: -0.0000

Data Index: 344531 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.5443. Min Act: -0.0000

Data Index: 430672 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.5239. Min Act: -0.0000

Data Index: 363287 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1205592 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.3375. Min Act: -0.0000

Data Index: 917700 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.4125. Min Act: -0.0000

Data Index: 846028 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.4982. Min Act: -0.0000

Data Index: 106859 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1298594 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 2.2282. Min Range: -2.2282

Max Act: 1.4946. Min Act: -0.0000

Data Index: 192299 (C4 (Web Text))

Max Activating Token Index: 429