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

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

Neuron 5189 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1337613 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1266529 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1125432 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6408. Min Act: -0.0000

Data Index: 593974 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6646. Min Act: -0.0000

Data Index: 991829 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6669. Min Act: -0.0000

Data Index: 928430 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6049. Min Act: -0.0000

Data Index: 411196 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6478. Min Act: -0.0000

Data Index: 774190 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6406. Min Act: -0.0000

Data Index: 892301 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6303. Min Act: -0.0000

Data Index: 347174 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5886. Min Act: -0.0000

Data Index: 438322 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6244. Min Act: -0.0000

Data Index: 82707 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1102012 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1108512 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6198. Min Act: -0.0000

Data Index: 757609 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1327410 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1312880 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5562. Min Act: -0.0000

Data Index: 438562 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5570. Min Act: -0.0000

Data Index: 299075 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5541. Min Act: -0.0000

Data Index: 613607 (C4 (Web Text))

Max Activating Token Index: 677