Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5507 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.8224. Min Act: -0.0001

Data Index: 54793 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.4348. Min Act: -0.0001

Data Index: 956777 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.4127. Min Act: -0.0001

Data Index: 13774 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.2139. Min Act: -0.0001

Data Index: 248266 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.4861. Min Act: -0.0001

Data Index: 537643 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.3146. Min Act: -0.0001

Data Index: 376353 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.3955. Min Act: -0.0001

Data Index: 115970 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.1319. Min Act: -0.0001

Data Index: 975376 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.2543. Min Act: -0.0001

Data Index: 875346 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.0342. Min Act: -0.0001

Data Index: 1114286 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.1709. Min Act: -0.0001

Data Index: 719950 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.1571. Min Act: -0.0001

Data Index: 282365 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.1336. Min Act: -0.0001

Data Index: 267478 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.1108. Min Act: -0.0001

Data Index: 123393 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.0279. Min Act: -0.0001

Data Index: 765258 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 3.8224. Min Range: -3.8224

Max Act: 2.8815. Min Act: -0.0001

Data Index: 1093931 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 3.8224. Min Range: -3.8224

Max Act: 2.8446. Min Act: -0.0001

Data Index: 495356 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.8224. Min Range: -3.8224

Max Act: 2.9496. Min Act: -0.0001

Data Index: 57695 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.1164. Min Act: -0.0001

Data Index: 717541 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 3.8224. Min Range: -3.8224

Max Act: 3.0753. Min Act: -0.0001

Data Index: 443076 (C4 (Web Text))

Max Activating Token Index: 1008