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

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

Neuron 1315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4256. Min Act: -0.0000

Data Index: 7515 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4314. Min Act: -0.0000

Data Index: 492166 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.4260. Min Act: -0.0001

Data Index: 764697 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1005855 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3980. Min Act: 0.0000

Data Index: 853493 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3936. Min Act: -0.0000

Data Index: 227633 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3962. Min Act: -0.0000

Data Index: 404485 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3816. Min Act: -0.0000

Data Index: 217411 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1291417 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3820. Min Act: -0.0000

Data Index: 573355 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3733. Min Act: -0.0000

Data Index: 493197 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3901. Min Act: -0.0000

Data Index: 956200 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3717. Min Act: -0.0000

Data Index: 365717 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3705. Min Act: -0.0000

Data Index: 257105 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3573. Min Act: -0.0000

Data Index: 950001 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3527. Min Act: -0.0000

Data Index: 831164 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1221691 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3457. Min Act: -0.0001

Data Index: 220636 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3524. Min Act: -0.0000

Data Index: 802419 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.4314. Min Range: -0.4314

Max Act: 0.3391. Min Act: -0.0000

Data Index: 817370 (C4 (Web Text))

Max Activating Token Index: 242