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

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

Neuron 5362 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.2618. Min Act: -0.0000

Data Index: 688374 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.9257. Min Act: -0.0000

Data Index: 187267 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.2514. Min Act: -0.0000

Data Index: 876111 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.1211. Min Act: -0.0000

Data Index: 592446 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.9335. Min Act: -0.0000

Data Index: 1296244 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.0438. Min Act: -0.0000

Data Index: 1163035 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.0206. Min Act: -0.0000

Data Index: 169876 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8999. Min Act: -0.0000

Data Index: 1329843 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8817. Min Act: -0.0000

Data Index: 1131610 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8696. Min Act: -0.0000

Data Index: 544084 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.0510. Min Act: -0.0000

Data Index: 685591 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8324. Min Act: -0.0000

Data Index: 335442 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8189. Min Act: -0.0000

Data Index: 582968 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.9039. Min Act: -0.0000

Data Index: 548717 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 2.2618. Min Range: -2.2618

Max Act: 2.0149. Min Act: -0.0000

Data Index: 976817 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.9156. Min Act: -0.0000

Data Index: 486700 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.7967. Min Act: -0.0000

Data Index: 336709 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1139506 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8071. Min Act: -0.0000

Data Index: 326417 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 2.2618. Min Range: -2.2618

Max Act: 1.8710. Min Act: -0.0000

Data Index: 912714 (C4 (Web Text))

Max Activating Token Index: 961