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

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

Neuron 4574 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7107. Min Range: -1.7107

Max Act: 1.7107. Min Act: -0.0000

Data Index: 1117427 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 1.7107. Min Range: -1.7107

Max Act: 1.1530. Min Act: -0.0000

Data Index: 1101578 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.9934. Min Act: -0.0000

Data Index: 1263519 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.9655. Min Act: -0.0000

Data Index: 523386 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8824. Min Act: -0.0000

Data Index: 92560 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8776. Min Act: -0.0000

Data Index: 66845 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7876. Min Act: -0.0000

Data Index: 867916 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8417. Min Act: -0.0000

Data Index: 635845 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8151. Min Act: -0.0000

Data Index: 100786 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1027919 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8273. Min Act: -0.0000

Data Index: 564545 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8127. Min Act: -0.0000

Data Index: 22684 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7625. Min Act: -0.0000

Data Index: 328598 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8044. Min Act: -0.0000

Data Index: 558234 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7978. Min Act: -0.0000

Data Index: 482042 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1067967 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.8315. Min Act: -0.0000

Data Index: 843126 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7244. Min Act: -0.0000

Data Index: 755559 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7547. Min Act: -0.0000

Data Index: 39707 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 1.7107. Min Range: -1.7107

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1167967 (C4 (Web Text))

Max Activating Token Index: 116