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

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

Neuron 5041 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2165. Min Range: -2.2165

Max Act: 2.2165. Min Act: -0.0000

Data Index: 1349062 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1469198 (Python Code)

Max Activating Token Index: 365

Text #2

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.5588. Min Act: -0.0000

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.2930. Min Act: -0.0000

Data Index: 786701 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.3493. Min Act: -0.0000

Data Index: 418548 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1492414 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1833. Min Act: -0.0000

Data Index: 1506068 (Python Code)

Max Activating Token Index: 343

Text #7

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1326656 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1625723 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1513756 (Python Code)

Max Activating Token Index: 985

Text #10

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.2669. Min Act: -0.0000

Data Index: 50840 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1745. Min Act: -0.0000

Data Index: 307189 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1057120 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1495248 (Python Code)

Max Activating Token Index: 1013

Text #14

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1609. Min Act: -0.0000

Data Index: 34510 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1567. Min Act: -0.0000

Data Index: 558857 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1213. Min Act: -0.0000

Data Index: 1378196 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1381503 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1329. Min Act: -0.0000

Data Index: 8465 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 2.2165. Min Range: -2.2165

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1084425 (C4 (Web Text))

Max Activating Token Index: 987