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

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

Neuron 4856 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5247. Min Range: -3.5247

Max Act: 3.5247. Min Act: -0.0000

Data Index: 1286175 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 3.5247. Min Range: -3.5247

Max Act: 3.1016. Min Act: -0.0000

Data Index: 1336662 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 3.5247. Min Range: -3.5247

Max Act: 3.1435. Min Act: -0.0000

Data Index: 270845 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.8658. Min Act: -0.0000

Data Index: 1290508 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.6723. Min Act: -0.0000

Data Index: 926909 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.5639. Min Act: -0.0000

Data Index: 1193253 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.5657. Min Act: -0.0000

Data Index: 1277062 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.1522. Min Act: -0.0000

Data Index: 1338413 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.0153. Min Act: -0.0000

Data Index: 403072 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.1719. Min Act: -0.0000

Data Index: 1159428 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.1157. Min Act: -0.0000

Data Index: 1228523 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.2537. Min Act: -0.0000

Data Index: 1042959 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 3.5247. Min Range: -3.5247

Max Act: 1.9884. Min Act: -0.0000

Data Index: 861557 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.0712. Min Act: -0.0000

Data Index: 443943 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 3.5247. Min Range: -3.5247

Max Act: 1.9289. Min Act: -0.0000

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 3.5247. Min Range: -3.5247

Max Act: 2.0358. Min Act: -0.0000

Data Index: 1349145 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.5247. Min Range: -3.5247

Max Act: 1.9936. Min Act: -0.0000

Data Index: 724519 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.5247. Min Range: -3.5247

Max Act: 1.9693. Min Act: -0.0000

Data Index: 159930 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 3.5247. Min Range: -3.5247

Max Act: 1.7430. Min Act: -0.0000

Data Index: 1251940 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 3.5247. Min Range: -3.5247

Max Act: 1.9524. Min Act: -0.0000

Data Index: 1340103 (C4 (Web Text))

Max Activating Token Index: 773