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

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

Neuron 829 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.9736. Min Act: -0.0000

Data Index: 219238 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 2.0796. Min Range: -2.0796

Max Act: 2.0796. Min Act: -0.0000

Data Index: 677347 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.9260. Min Act: -0.0000

Data Index: 1339069 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.8869. Min Act: -0.0000

Data Index: 1394509 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.8345. Min Act: -0.0000

Data Index: 593937 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7376. Min Act: -0.0000

Data Index: 889810 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7590. Min Act: -0.0000

Data Index: 736057 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7646. Min Act: -0.0000

Data Index: 944931 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.7539. Min Act: -0.0000

Data Index: 884947 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.8102. Min Act: -0.0000

Data Index: 553281 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.8077. Min Act: -0.0000

Data Index: 1161448 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6990. Min Act: 0.0000

Data Index: 1283027 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6142. Min Act: -0.0000

Data Index: 85513 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6763. Min Act: -0.0000

Data Index: 764346 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6477. Min Act: -0.0000

Data Index: 1021431 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6471. Min Act: -0.0000

Data Index: 28427 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6355. Min Act: -0.0000

Data Index: 84929 (C4 (Web Text))

Max Activating Token Index: 788

Text #17

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6310. Min Act: 0.0000

Data Index: 866407 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6152. Min Act: -0.0000

Data Index: 448501 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 2.0796. Min Range: -2.0796

Max Act: 1.6709. Min Act: -0.0000

Data Index: 914246 (C4 (Web Text))

Max Activating Token Index: 546