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

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

Neuron 2940 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.8295. Min Act: -0.0002

Data Index: 22800 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6808. Min Act: -0.0001

Data Index: 1014099 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.7006. Min Act: -0.0001

Data Index: 832335 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.7165. Min Act: -0.0002

Data Index: 919969 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6934. Min Act: -0.0001

Data Index: 1292116 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6866. Min Act: -0.0002

Data Index: 126361 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6841. Min Act: -0.0001

Data Index: 381455 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6798. Min Act: -0.0002

Data Index: 714387 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6788. Min Act: -0.0002

Data Index: 605299 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6294. Min Act: -0.0001

Data Index: 659583 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6707. Min Act: -0.0001

Data Index: 87229 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6677. Min Act: -0.0001

Data Index: 615163 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6419. Min Act: -0.0001

Data Index: 1244159 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6598. Min Act: -0.0001

Data Index: 800007 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6549. Min Act: -0.0001

Data Index: 915223 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6508. Min Act: -0.0002

Data Index: 1356139 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6339. Min Act: -0.0001

Data Index: 889493 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6308. Min Act: -0.0001

Data Index: 1247135 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6444. Min Act: -0.0001

Data Index: 1308563 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.8295. Min Range: -0.8295

Max Act: 0.6155. Min Act: -0.0001

Data Index: 811334 (C4 (Web Text))

Max Activating Token Index: 65