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

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

Neuron 3499 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.6425. Min Act: -0.0000

Data Index: 406968 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5699. Min Act: -0.0000

Data Index: 460890 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1291590 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5301. Min Act: -0.0000

Data Index: 17101 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5165. Min Act: 0.0000

Data Index: 269133 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4920. Min Act: -0.0000

Data Index: 914731 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5218. Min Act: -0.0000

Data Index: 947062 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1334031 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1496410 (Python Code)

Max Activating Token Index: 888

Text #9

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4466. Min Act: -0.0000

Data Index: 818363 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4910. Min Act: -0.0000

Data Index: 301036 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4818. Min Act: -0.0000

Data Index: 296842 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1056278 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1190792 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4460. Min Act: -0.0000

Data Index: 73679 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4479. Min Act: -0.0000

Data Index: 925021 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4671. Min Act: -0.0000

Data Index: 911935 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4642. Min Act: -0.0000

Data Index: 251999 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4455. Min Act: -0.0000

Data Index: 99153 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4656. Min Act: -0.0000

Data Index: 467319 (C4 (Web Text))

Max Activating Token Index: 259