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

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

Neuron 1985 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: 0.8386. Min Range: -0.8386

Max Act: 0.8061. Min Act: -0.0000

Data Index: 172624 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7752. Min Act: -0.0000

Data Index: 334594 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7945. Min Act: -0.0000

Data Index: 770345 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1400623 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7298. Min Act: -0.0000

Data Index: 394238 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.7239. Min Act: -0.0000

Data Index: 48326 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6922. Min Act: -0.0000

Data Index: 266853 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1083037 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6621. Min Act: -0.0000

Data Index: 754257 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6821. Min Act: -0.0000

Data Index: 871628 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6767. Min Act: -0.0000

Data Index: 203690 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6657. Min Act: -0.0000

Data Index: 780980 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6638. Min Act: -0.0000

Data Index: 1252199 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1328107 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1092530 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6340. Min Act: -0.0000

Data Index: 240423 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6213. Min Act: -0.0000

Data Index: 834049 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6159. Min Act: -0.0000

Data Index: 769389 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6136. Min Act: -0.0000

Data Index: 495092 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.8386. Min Range: -0.8386

Max Act: 0.6009. Min Act: -0.0000

Data Index: 112412 (C4 (Web Text))

Max Activating Token Index: 89