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

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

Neuron 5880 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.5467. Min Act: -0.0001

Data Index: 960386 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.5351. Min Act: -0.0001

Data Index: 1313946 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.5179. Min Act: -0.0001

Data Index: 112462 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.7049. Min Act: -0.0001

Data Index: 959492 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.4200. Min Act: -0.0001

Data Index: 532638 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.2258. Min Act: -0.0001

Data Index: 901537 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.3423. Min Act: -0.0001

Data Index: 1213814 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.3096. Min Act: -0.0001

Data Index: 331043 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.8249. Min Act: -0.0001

Data Index: 501340 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.4597. Min Act: -0.0001

Data Index: 256467 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.3537. Min Act: -0.0001

Data Index: 925063 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.4190. Min Act: -0.0001

Data Index: 310822 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.2266. Min Act: -0.0001

Data Index: 1064017 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.3526. Min Act: -0.0001

Data Index: 353459 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.2852. Min Act: -0.0001

Data Index: 353390 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.2316. Min Act: -0.0001

Data Index: 294067 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.1059. Min Act: -0.0001

Data Index: 1252891 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1270974 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.1289. Min Act: -0.0001

Data Index: 412646 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.8249. Min Range: -1.8249

Max Act: 1.2615. Min Act: -0.0001

Data Index: 311053 (C4 (Web Text))

Max Activating Token Index: 8