Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.2802. Min Act: -0.0000

Data Index: 684134 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.2946. Min Act: -0.0000

Data Index: 968847 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1336797 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.2140. Min Act: -0.0000

Data Index: 1342420 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.2099. Min Act: -0.0000

Data Index: 409536 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.1377. Min Act: -0.0000

Data Index: 882136 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0970. Min Act: -0.0000

Data Index: 116819 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0954. Min Act: -0.0000

Data Index: 705191 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0911. Min Act: -0.0000

Data Index: 496567 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0927. Min Act: -0.0000

Data Index: 972701 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1107306 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1281648 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0554. Min Act: -0.0000

Data Index: 298557 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0441. Min Act: 0.0000

Data Index: 25805 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0278. Min Act: 0.0000

Data Index: 763221 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 1.2946. Min Range: -1.2946

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1154970 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0532. Min Act: -0.0000

Data Index: 7511 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0145. Min Act: -0.0000

Data Index: 831010 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 1.2946. Min Range: -1.2946

Max Act: 1.0015. Min Act: -0.0000

Data Index: 904306 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.2946. Min Range: -1.2946

Max Act: 0.9904. Min Act: -0.0000

Data Index: 936582 (C4 (Web Text))

Max Activating Token Index: 373