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

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

Neuron 3473 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7402. Min Range: -2.7402

Max Act: 2.7402. Min Act: -0.0000

Data Index: 1610964 (Python Code)

Max Activating Token Index: 1000

Text #1

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.9371. Min Act: -0.0000

Data Index: 331614 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.7084. Min Act: -0.0000

Data Index: 241755 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.7158. Min Act: -0.0000

Data Index: 1350205 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.4662. Min Act: -0.0000

Data Index: 311517 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1228930 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1633690 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.3541. Min Act: -0.0000

Data Index: 1031573 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.2548. Min Act: -0.0000

Data Index: 180128 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1146119 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1381784 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.3111. Min Act: -0.0000

Data Index: 1411191 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1463735 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.2974. Min Act: -0.0000

Data Index: 252415 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1020641 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.2400. Min Act: -0.0000

Data Index: 366034 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1428626 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.1986. Min Act: -0.0000

Data Index: 528473 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1418572 (Python Code)

Max Activating Token Index: 380

Text #19

Max Range: 2.7402. Min Range: -2.7402

Max Act: 1.2350. Min Act: -0.0000

Data Index: 795173 (C4 (Web Text))

Max Activating Token Index: 947