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

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

Neuron 644 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.1182. Min Act: -0.0000

Data Index: 618269 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.0070. Min Act: -0.0000

Data Index: 86132 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.1112. Min Act: -0.0000

Data Index: 1164805 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 2.2312. Min Range: -2.2312

Max Act: 2.2312. Min Act: -0.0000

Data Index: 1118627 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9808. Min Act: -0.0000

Data Index: 289692 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9696. Min Act: -0.0000

Data Index: 435314 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.9694. Min Act: -0.0000

Data Index: 1266642 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1323685 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.7807. Min Act: -0.0000

Data Index: 922621 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.7736. Min Act: -0.0000

Data Index: 942812 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.7340. Min Act: -0.0000

Data Index: 606361 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.7262. Min Act: -0.0000

Data Index: 1094896 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.7249. Min Act: -0.0000

Data Index: 610576 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.6952. Min Act: -0.0000

Data Index: 96705 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.6707. Min Act: -0.0000

Data Index: 1200981 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.6607. Min Act: -0.0000

Data Index: 1190504 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.6676. Min Act: -0.0000

Data Index: 1157537 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.5623. Min Act: -0.0000

Data Index: 109968 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1133004 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 2.2312. Min Range: -2.2312

Max Act: 1.5073. Min Act: -0.0000

Data Index: 935963 (C4 (Web Text))

Max Activating Token Index: 852