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

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

Neuron 282 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1249597 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.6376. Min Act: -0.0000

Data Index: 514340 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1199404 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1270004 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.6344. Min Act: -0.0001

Data Index: 844334 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5924. Min Act: -0.0001

Data Index: 543297 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5479. Min Act: -0.0000

Data Index: 702383 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5578. Min Act: -0.0001

Data Index: 1278323 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5777. Min Act: -0.0000

Data Index: 15494 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5556. Min Act: -0.0000

Data Index: 387684 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1326293 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5567. Min Act: -0.0001

Data Index: 853615 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5381. Min Act: -0.0001

Data Index: 510303 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5047. Min Act: -0.0000

Data Index: 578612 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1302482 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5344. Min Act: -0.0001

Data Index: 6484 (C4 (Web Text))

Max Activating Token Index: 124

Text #16

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5277. Min Act: -0.0001

Data Index: 225461 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5024. Min Act: -0.0001

Data Index: 1510777 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.4997. Min Act: -0.0001

Data Index: 1210022 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.6376. Min Range: -0.6376

Max Act: 0.5004. Min Act: -0.0001

Data Index: 325709 (C4 (Web Text))

Max Activating Token Index: 791