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

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

Neuron 361 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: 2.0320. Min Range: -2.0320

Max Act: 2.0320. Min Act: -0.0000

Data Index: 933047 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.5290. Min Act: -0.0000

Data Index: 9259 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.5022. Min Act: -0.0000

Data Index: 494027 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.4468. Min Act: -0.0000

Data Index: 249113 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3283. Min Act: -0.0000

Data Index: 589788 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3988. Min Act: -0.0000

Data Index: 3313 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3964. Min Act: -0.0000

Data Index: 1262252 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3419. Min Act: -0.0000

Data Index: 579026 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1122539 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3386. Min Act: -0.0000

Data Index: 539806 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.3376. Min Act: -0.0000

Data Index: 1075441 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2215. Min Act: -0.0000

Data Index: 339881 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2752. Min Act: -0.0000

Data Index: 386056 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2100. Min Act: -0.0000

Data Index: 659268 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2707. Min Act: -0.0000

Data Index: 291969 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2558. Min Act: -0.0000

Data Index: 970149 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2552. Min Act: -0.0000

Data Index: 365688 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2522. Min Act: -0.0000

Data Index: 312955 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2410. Min Act: -0.0000

Data Index: 343501 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 2.0320. Min Range: -2.0320

Max Act: 1.2314. Min Act: -0.0000

Data Index: 599695 (C4 (Web Text))

Max Activating Token Index: 777