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

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

Neuron 2200 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: 1.1384. Min Range: -1.1384

Max Act: 1.1384. Min Act: -0.0001

Data Index: 614346 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.1384. Min Range: -1.1384

Max Act: 1.0203. Min Act: -0.0001

Data Index: 1311417 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9245. Min Act: -0.0001

Data Index: 140032 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9837. Min Act: -0.0001

Data Index: 130211 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9407. Min Act: -0.0001

Data Index: 956236 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9919. Min Act: -0.0001

Data Index: 1120028 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9503. Min Act: -0.0001

Data Index: 198709 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9734. Min Act: -0.0001

Data Index: 758006 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8399. Min Act: -0.0001

Data Index: 88624 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8585. Min Act: -0.0001

Data Index: 544161 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9311. Min Act: -0.0001

Data Index: 1234807 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1194560 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1195113 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8252. Min Act: -0.0001

Data Index: 1174435 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1138884 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8287. Min Act: -0.0001

Data Index: 376085 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.9498. Min Act: -0.0001

Data Index: 464508 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8448. Min Act: -0.0001

Data Index: 1634000 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8451. Min Act: -0.0001

Data Index: 261779 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 1.1384. Min Range: -1.1384

Max Act: 0.8392. Min Act: -0.0001

Data Index: 443126 (C4 (Web Text))

Max Activating Token Index: 394