Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3789 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5443. Min Act: -0.0000

Data Index: 294672 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5628. Min Act: -0.0000

Data Index: 211817 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1548199 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5856. Min Act: -0.0000

Data Index: 224877 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5344. Min Act: -0.0000

Data Index: 787620 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1490485 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4608. Min Act: -0.0000

Data Index: 411096 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5323. Min Act: -0.0000

Data Index: 882919 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5097. Min Act: -0.0000

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4740. Min Act: -0.0000

Data Index: 961119 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4915. Min Act: -0.0000

Data Index: 194408 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4745. Min Act: -0.0000

Data Index: 705306 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1200885 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4573. Min Act: -0.0000

Data Index: 120322 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1174407 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4548. Min Act: -0.0000

Data Index: 246457 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4713. Min Act: -0.0000

Data Index: 822038 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.5005. Min Act: -0.0000

Data Index: 665171 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4683. Min Act: -0.0000

Data Index: 215254 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.5856. Min Range: -0.5856

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1055496 (C4 (Web Text))

Max Activating Token Index: 540