Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3807 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.5503. Min Act: -0.0003

Data Index: 63987 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4773. Min Act: -0.0003

Data Index: 886760 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4600. Min Act: -0.0003

Data Index: 1129890 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4638. Min Act: -0.0003

Data Index: 280455 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4364. Min Act: -0.0003

Data Index: 861490 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4756. Min Act: -0.0004

Data Index: 1256151 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4451. Min Act: -0.0003

Data Index: 4421 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4229. Min Act: -0.0003

Data Index: 1106906 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4011. Min Act: -0.0003

Data Index: 499516 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.3867. Min Act: -0.0003

Data Index: 498524 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4226. Min Act: -0.0003

Data Index: 978512 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4612. Min Act: -0.0003

Data Index: 1144147 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.3760. Min Act: -0.0003

Data Index: 603804 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.3401. Min Act: -0.0003

Data Index: 457591 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4730. Min Act: -0.0003

Data Index: 1061529 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4572. Min Act: -0.0003

Data Index: 1142057 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4715. Min Act: -0.0003

Data Index: 1126824 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4252. Min Act: -0.0003

Data Index: 64044 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4391. Min Act: -0.0003

Data Index: 1084542 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.5503. Min Range: -0.5503

Max Act: 0.4858. Min Act: -0.0003

Data Index: 667975 (C4 (Web Text))

Max Activating Token Index: 884