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

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

Neuron 4431 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: 1.1436. Min Range: -1.1436

Max Act: 1.1436. Min Act: -0.0000

Data Index: 643244 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.1417. Min Act: -0.0000

Data Index: 191575 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.1312. Min Act: -0.0001

Data Index: 1201993 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.1360. Min Act: -0.0001

Data Index: 1152377 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1184421 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0712. Min Act: -0.0001

Data Index: 944440 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0629. Min Act: -0.0001

Data Index: 449105 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0651. Min Act: -0.0001

Data Index: 273360 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0491. Min Act: -0.0000

Data Index: 691650 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.9998. Min Act: -0.0000

Data Index: 402295 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.9912. Min Act: -0.0001

Data Index: 910146 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0556. Min Act: -0.0001

Data Index: 153598 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.9542. Min Act: -0.0000

Data Index: 114057 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0203. Min Act: -0.0001

Data Index: 834441 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.8143. Min Act: -0.0001

Data Index: 605277 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.9158. Min Act: -0.0001

Data Index: 238952 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.9679. Min Act: -0.0001

Data Index: 780298 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0494. Min Act: -0.0001

Data Index: 9506 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 1.1436. Min Range: -1.1436

Max Act: 1.0325. Min Act: -0.0001

Data Index: 125121 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.1436. Min Range: -1.1436

Max Act: 0.8999. Min Act: -0.0000

Data Index: 559360 (C4 (Web Text))

Max Activating Token Index: 214