Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 36 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2224. Min Range: -3.2224

Max Act: 3.2224. Min Act: -0.0000

Data Index: 1261438 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.9074. Min Act: -0.0000

Data Index: 465290 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.6575. Min Act: -0.0000

Data Index: 886288 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.4089. Min Act: -0.0000

Data Index: 975043 (C4 (Web Text))

Max Activating Token Index: 457

Text #4

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.5053. Min Act: -0.0000

Data Index: 1297962 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.5415. Min Act: -0.0000

Data Index: 505237 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.3522. Min Act: -0.0000

Data Index: 650384 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.2975. Min Act: -0.0000

Data Index: 1322723 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.2224. Min Range: -3.2224

Max Act: 1.9509. Min Act: -0.0000

Data Index: 592877 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.0462. Min Act: -0.0000

Data Index: 1169923 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.1428. Min Act: -0.0000

Data Index: 285925 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.1613. Min Act: -0.0000

Data Index: 103796 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.2582. Min Act: -0.0000

Data Index: 1307627 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.1165. Min Act: -0.0000

Data Index: 1109923 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.1208. Min Act: -0.0000

Data Index: 1010072 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.1194. Min Act: -0.0000

Data Index: 1103941 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.0745. Min Act: -0.0000

Data Index: 855162 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.1460. Min Act: -0.0000

Data Index: 931701 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.0425. Min Act: -0.0000

Data Index: 1202092 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 3.2224. Min Range: -3.2224

Max Act: 2.0197. Min Act: -0.0000

Data Index: 1076623 (C4 (Web Text))

Max Activating Token Index: 522