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

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

Neuron 3832 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: 8.5238. Min Range: -8.5238

Max Act: 8.5238. Min Act: 0.0002

Data Index: 677866 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 8.5238. Min Range: -8.5238

Max Act: 8.2742. Min Act: -0.0000

Data Index: 739752 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.9599. Min Act: -0.0000

Data Index: 64242 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 8.5238. Min Range: -8.5238

Max Act: 6.1487. Min Act: -0.0000

Data Index: 920533 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 8.5238. Min Range: -8.5238

Max Act: 6.0527. Min Act: -0.0000

Data Index: 494708 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.9100. Min Act: 0.0001

Data Index: 668759 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.8876. Min Act: 0.0000

Data Index: 641617 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.7404. Min Act: -0.0000

Data Index: 671082 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.4881. Min Act: -0.0000

Data Index: 132957 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.6551. Min Act: 0.0000

Data Index: 634153 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.0792. Min Act: -0.0000

Data Index: 1170174 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.2401. Min Act: -0.0000

Data Index: 537197 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.2434. Min Act: 0.0000

Data Index: 445958 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.3829. Min Act: -0.0000

Data Index: 889683 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 8.5238. Min Range: -8.5238

Max Act: 5.0570. Min Act: -0.0000

Data Index: 291761 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 8.5238. Min Range: -8.5238

Max Act: 4.9503. Min Act: -0.0000

Data Index: 880376 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 8.5238. Min Range: -8.5238

Max Act: 4.9327. Min Act: -0.0000

Data Index: 1193529 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 8.5238. Min Range: -8.5238

Max Act: 4.7609. Min Act: -0.0000

Data Index: 1004494 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 8.5238. Min Range: -8.5238

Max Act: 4.7538. Min Act: -0.0000

Data Index: 753909 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 8.5238. Min Range: -8.5238

Max Act: 4.7662. Min Act: -0.0000

Data Index: 565195 (C4 (Web Text))

Max Activating Token Index: 670