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

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

Neuron 2999 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1196114 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1337407 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2876. Min Act: -0.0000

Data Index: 60076 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1032527 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2548. Min Act: -0.0001

Data Index: 502379 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1142582 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2519. Min Act: -0.0001

Data Index: 143241 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2500. Min Act: -0.0001

Data Index: 704429 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2605. Min Act: -0.0000

Data Index: 42765 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2521. Min Act: -0.0001

Data Index: 902830 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1087385 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2512. Min Act: -0.0000

Data Index: 816411 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2581. Min Act: -0.0001

Data Index: 448021 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2155. Min Act: -0.0000

Data Index: 324808 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2368. Min Act: -0.0001

Data Index: 403161 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2007. Min Act: -0.0000

Data Index: 980245 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2196. Min Act: -0.0000

Data Index: 927558 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2367. Min Act: -0.0001

Data Index: 560618 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1266500 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.3258. Min Range: -0.3258

Max Act: 0.2379. Min Act: -0.0000

Data Index: 796725 (C4 (Web Text))

Max Activating Token Index: 27