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

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

Neuron 4654 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.7909. Min Act: -0.0000

Data Index: 278114 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.9252. Min Act: -0.0000

Data Index: 406790 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.9202. Min Act: -0.0000

Data Index: 360774 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.9223. Min Act: -0.0000

Data Index: 1302427 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.7469. Min Act: -0.0000

Data Index: 1214569 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1211917 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 2.0302. Min Range: -2.0302

Max Act: 2.0302. Min Act: -0.0000

Data Index: 1247231 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6307. Min Act: -0.0000

Data Index: 397420 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.7489. Min Act: -0.0000

Data Index: 1281506 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.7334. Min Act: -0.0000

Data Index: 790070 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.5688. Min Act: -0.0000

Data Index: 330821 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6394. Min Act: -0.0000

Data Index: 914840 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.8401. Min Act: -0.0000

Data Index: 353178 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6212. Min Act: -0.0000

Data Index: 660840 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6138. Min Act: -0.0000

Data Index: 698853 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1296697 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6152. Min Act: -0.0000

Data Index: 487378 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.6520. Min Act: -0.0000

Data Index: 817213 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.5986. Min Act: -0.0000

Data Index: 1097950 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 2.0302. Min Range: -2.0302

Max Act: 1.4230. Min Act: -0.0000

Data Index: 1303864 (C4 (Web Text))

Max Activating Token Index: 385