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

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

Neuron 1828 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0468. Min Act: -0.0001

Data Index: 648261 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0400. Min Act: -0.0001

Data Index: 1181259 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0384. Min Act: -0.0002

Data Index: 227696 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0397. Min Act: -0.0001

Data Index: 708300 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1327137 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0366. Min Act: -0.0002

Data Index: 554485 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1348349 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0345. Min Act: -0.0001

Data Index: 853167 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0356. Min Act: -0.0001

Data Index: 813419 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1390269 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0320. Min Act: -0.0002

Data Index: 162943 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1502649 (Python Code)

Max Activating Token Index: 488

Text #12

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0330. Min Act: -0.0001

Data Index: 576546 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0363. Min Act: -0.0001

Data Index: 667734 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0321. Min Act: -0.0001

Data Index: 711159 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0335. Min Act: -0.0001

Data Index: 855382 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0324. Min Act: -0.0001

Data Index: 330208 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0316. Min Act: -0.0001

Data Index: 837025 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1582169 (Python Code)

Max Activating Token Index: 921

Text #19

Max Range: 0.0468. Min Range: -0.0468

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1268425 (C4 (Web Text))

Max Activating Token Index: 24