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

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

Neuron 5030 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2637. Min Range: -1.2637

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1212432 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 1.2637. Min Range: -1.2637

Max Act: 1.0734. Min Act: -0.0000

Data Index: 538952 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1028563 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1221984 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.8486. Min Act: -0.0000

Data Index: 978011 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7287. Min Act: -0.0000

Data Index: 194883 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7655. Min Act: -0.0000

Data Index: 105106 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7547. Min Act: -0.0000

Data Index: 520457 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1275519 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7504. Min Act: -0.0000

Data Index: 268298 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7981. Min Act: -0.0000

Data Index: 701124 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7185. Min Act: -0.0000

Data Index: 441757 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1126019 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.7003. Min Act: -0.0000

Data Index: 248472 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6872. Min Act: 0.0000

Data Index: 1042194 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6606. Min Act: -0.0000

Data Index: 498423 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6377. Min Act: -0.0000

Data Index: 226673 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6526. Min Act: -0.0000

Data Index: 856821 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6094. Min Act: -0.0000

Data Index: 166873 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.2637. Min Range: -1.2637

Max Act: 0.6445. Min Act: -0.0000

Data Index: 551526 (C4 (Web Text))

Max Activating Token Index: 319