Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 389 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.4322. Min Act: -0.0000

Data Index: 592555 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.4426. Min Act: -0.0001

Data Index: 583061 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.3479. Min Act: -0.0001

Data Index: 1218882 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.2562. Min Act: -0.0001

Data Index: 1248148 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.3203. Min Act: -0.0001

Data Index: 926087 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1852. Min Act: -0.0001

Data Index: 100601 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.2479. Min Act: -0.0000

Data Index: 513591 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.0961. Min Act: -0.0001

Data Index: 738702 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1798. Min Act: -0.0001

Data Index: 62461 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.2460. Min Act: -0.0001

Data Index: 1208589 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.2038. Min Act: -0.0000

Data Index: 684961 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1598. Min Act: -0.0001

Data Index: 550579 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.0839. Min Act: -0.0001

Data Index: 415472 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1508. Min Act: -0.0001

Data Index: 476284 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1311. Min Act: -0.0001

Data Index: 246280 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1237. Min Act: -0.0001

Data Index: 212885 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.1025. Min Act: -0.0001

Data Index: 193423 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.2067. Min Act: -0.0001

Data Index: 229026 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.0976. Min Act: -0.0001

Data Index: 899339 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.4426. Min Range: -1.4426

Max Act: 1.0635. Min Act: -0.0000

Data Index: 918597 (C4 (Web Text))

Max Activating Token Index: 239