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

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

Neuron 3479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4619. Min Act: -0.0001

Data Index: 312827 (C4 (Web Text))

Max Activating Token Index: 399

Text #1

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4977. Min Act: -0.0001

Data Index: 544250 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1228543 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1244522 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4117. Min Act: -0.0001

Data Index: 703032 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4347. Min Act: -0.0001

Data Index: 535427 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4532. Min Act: -0.0001

Data Index: 783570 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4176. Min Act: -0.0001

Data Index: 630097 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4492. Min Act: -0.0001

Data Index: 445225 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4071. Min Act: -0.0001

Data Index: 664519 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4410. Min Act: -0.0001

Data Index: 585030 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4341. Min Act: -0.0001

Data Index: 1062109 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3830. Min Act: -0.0001

Data Index: 291111 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4156. Min Act: -0.0001

Data Index: 84733 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3888. Min Act: -0.0001

Data Index: 393589 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4132. Min Act: -0.0001

Data Index: 94948 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1305311 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3997. Min Act: -0.0001

Data Index: 495525 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.3674. Min Act: -0.0001

Data Index: 1005751 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.4977. Min Range: -0.4977

Max Act: 0.4044. Min Act: -0.0001

Data Index: 241301 (C4 (Web Text))

Max Activating Token Index: 932