Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1052 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0444. Min Range: -1.0444

Max Act: 1.0444. Min Act: -0.0000

Data Index: 840241 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9347. Min Act: -0.0000

Data Index: 79227 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9228. Min Act: -0.0001

Data Index: 767891 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1109961 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.9219. Min Act: -0.0001

Data Index: 908832 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8519. Min Act: -0.0000

Data Index: 429653 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8293. Min Act: -0.0001

Data Index: 204400 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.8685. Min Act: -0.0001

Data Index: 948435 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7519. Min Act: -0.0001

Data Index: 543678 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1050501 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6697. Min Act: -0.0001

Data Index: 950974 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7024. Min Act: -0.0001

Data Index: 515723 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7236. Min Act: -0.0000

Data Index: 931978 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1307207 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1039223 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7175. Min Act: -0.0001

Data Index: 1356885 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6795. Min Act: -0.0000

Data Index: 241833 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.6768. Min Act: -0.0000

Data Index: 931108 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7332. Min Act: -0.0001

Data Index: 70247 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 1.0444. Min Range: -1.0444

Max Act: 0.7133. Min Act: -0.0001

Data Index: 540793 (C4 (Web Text))

Max Activating Token Index: 201