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

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

Neuron 2967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2544. Min Range: -4.2544

Max Act: 4.2544. Min Act: -0.0001

Data Index: 1107023 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 4.2544. Min Range: -4.2544

Max Act: 4.0314. Min Act: -0.0001

Data Index: 905680 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.9887. Min Act: -0.0001

Data Index: 341448 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 4.2544. Min Range: -4.2544

Max Act: 4.0001. Min Act: -0.0001

Data Index: 599192 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.7747. Min Act: -0.0001

Data Index: 1040855 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5921. Min Act: -0.0001

Data Index: 489346 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.7028. Min Act: -0.0001

Data Index: 1271979 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.8360. Min Act: -0.0001

Data Index: 715248 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.6912. Min Act: -0.0001

Data Index: 689065 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5389. Min Act: -0.0001

Data Index: 1132597 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.6295. Min Act: -0.0001

Data Index: 760653 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.6206. Min Act: -0.0001

Data Index: 106288 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5988. Min Act: -0.0001

Data Index: 303047 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.7317. Min Act: -0.0001

Data Index: 792273 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.4344. Min Act: -0.0001

Data Index: 812322 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5890. Min Act: -0.0001

Data Index: 700709 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5673. Min Act: -0.0001

Data Index: 588453 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5569. Min Act: -0.0001

Data Index: 111009 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.4028. Min Act: -0.0001

Data Index: 970009 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 4.2544. Min Range: -4.2544

Max Act: 3.5558. Min Act: -0.0001

Data Index: 1299775 (C4 (Web Text))

Max Activating Token Index: 661