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

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

Neuron 3479 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.2653. Min Act: -0.0001

Data Index: 820248 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1535. Min Act: -0.0000

Data Index: 399727 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1622. Min Act: -0.0000

Data Index: 182918 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1474. Min Act: -0.0000

Data Index: 977471 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1069294 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1331. Min Act: -0.0000

Data Index: 644327 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1304. Min Act: -0.0000

Data Index: 597458 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1222656 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1311. Min Act: -0.0000

Data Index: 147095 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1423. Min Act: -0.0000

Data Index: 625726 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1267. Min Act: -0.0000

Data Index: 854164 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1323. Min Act: -0.0000

Data Index: 474461 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1176. Min Act: -0.0000

Data Index: 614872 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1312. Min Act: -0.0000

Data Index: 180562 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1405. Min Act: -0.0000

Data Index: 585737 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1283. Min Act: -0.0000

Data Index: 913065 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1188. Min Act: -0.0000

Data Index: 55629 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1226. Min Act: -0.0000

Data Index: 775463 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1239. Min Act: -0.0000

Data Index: 338950 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.2653. Min Range: -0.2653

Max Act: 0.1165. Min Act: -0.0000

Data Index: 298125 (C4 (Web Text))

Max Activating Token Index: 554