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

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

Neuron 3004 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.9215. Min Act: -0.0000

Data Index: 188055 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.4936. Min Act: -0.0000

Data Index: 21047 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.2284. Min Act: -0.0000

Data Index: 1146486 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.2011. Min Act: -0.0000

Data Index: 630065 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.1332. Min Act: -0.0000

Data Index: 606747 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1498472 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1501630 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1392066 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.0526. Min Act: 0.0000

Data Index: 1459901 (Python Code)

Max Activating Token Index: 332

Text #9

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1547468 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1028282 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9973. Min Act: -0.0000

Data Index: 863057 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.0218. Min Act: -0.0000

Data Index: 936686 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9667. Min Act: -0.0000

Data Index: 574035 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9949. Min Act: -0.0000

Data Index: 11053 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9523. Min Act: -0.0000

Data Index: 199000 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.9215. Min Range: -1.9215

Max Act: 1.0064. Min Act: -0.0000

Data Index: 493654 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9709. Min Act: -0.0000

Data Index: 1265628 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9980. Min Act: -0.0000

Data Index: 1112182 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.9215. Min Range: -1.9215

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1235027 (C4 (Web Text))

Max Activating Token Index: 345