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

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

Neuron 4725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.2466. Min Act: -0.0000

Data Index: 829667 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1846. Min Act: -0.0000

Data Index: 980478 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1011. Min Act: -0.0000

Data Index: 606451 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0280. Min Act: -0.0000

Data Index: 483435 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0672. Min Act: -0.0000

Data Index: 202294 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0698. Min Act: -0.0000

Data Index: 170331 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0638. Min Act: -0.0000

Data Index: 546365 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0547. Min Act: -0.0000

Data Index: 566766 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1330459 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1232155 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1280822 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1127736 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0714. Min Act: -0.0000

Data Index: 274774 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.9557. Min Act: -0.0000

Data Index: 362361 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.2466. Min Range: -1.2466

Max Act: 1.0467. Min Act: -0.0000

Data Index: 631918 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.9254. Min Act: -0.0000

Data Index: 650494 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.9642. Min Act: -0.0000

Data Index: 608741 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.9664. Min Act: -0.0000

Data Index: 325475 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 1.2466. Min Range: -1.2466

Max Act: 0.9614. Min Act: -0.0000

Data Index: 519060 (C4 (Web Text))

Max Activating Token Index: 765