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

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

Neuron 1788 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0352. Min Act: -0.0001

Data Index: 662083 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1251214 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0362. Min Act: -0.0001

Data Index: 227148 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0333. Min Act: -0.0001

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0001

Data Index: 40558 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1419627 (Python Code)

Max Activating Token Index: 396

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1111057 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0329. Min Act: -0.0001

Data Index: 16726 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0312. Min Act: -0.0001

Data Index: 528862 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1151267 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0360. Min Act: -0.0001

Data Index: 58216 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0332. Min Act: -0.0001

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0319. Min Act: -0.0001

Data Index: 905724 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1345605 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0304. Min Act: -0.0001

Data Index: 932257 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1245329 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0295. Min Act: -0.0001

Data Index: 480509 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1258800 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1600430 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0303. Min Act: -0.0001

Data Index: 370506 (C4 (Web Text))

Max Activating Token Index: 465