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

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

Neuron 1002 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: 1.7606. Min Range: -1.7606

Max Act: 1.6206. Min Act: -0.0001

Data Index: 230593 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.7442. Min Act: -0.0002

Data Index: 417836 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.7029. Min Act: -0.0001

Data Index: 544573 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.5613. Min Act: -0.0002

Data Index: 769173 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.5463. Min Act: -0.0001

Data Index: 921612 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4339. Min Act: -0.0001

Data Index: 928234 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.7606. Min Act: -0.0002

Data Index: 423982 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.5297. Min Act: -0.0001

Data Index: 1114668 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4823. Min Act: -0.0001

Data Index: 1348024 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.6356. Min Act: -0.0001

Data Index: 697996 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.5535. Min Act: -0.0001

Data Index: 1197816 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4796. Min Act: -0.0002

Data Index: 440509 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4607. Min Act: -0.0001

Data Index: 165236 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.3789. Min Act: -0.0001

Data Index: 1096367 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4855. Min Act: -0.0001

Data Index: 1294351 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4391. Min Act: -0.0002

Data Index: 16741 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4340. Min Act: -0.0001

Data Index: 634906 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.5126. Min Act: -0.0002

Data Index: 32244 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4858. Min Act: -0.0002

Data Index: 405513 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.7606. Min Range: -1.7606

Max Act: 1.4055. Min Act: -0.0001

Data Index: 1088767 (C4 (Web Text))

Max Activating Token Index: 1010