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

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

Neuron 5560 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0000

Data Index: 1505130 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0289. Min Act: -0.0000

Data Index: 458366 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1018891 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0334. Min Act: -0.0000

Data Index: 1413538 (Python Code)

Max Activating Token Index: 712

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0312. Min Act: -0.0000

Data Index: 7333 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0280. Min Act: -0.0000

Data Index: 1546053 (Python Code)

Max Activating Token Index: 996

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1386540 (Python Code)

Max Activating Token Index: 239

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0275. Min Act: -0.0000

Data Index: 528558 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1421130 (Python Code)

Max Activating Token Index: 156

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1166921 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1552264 (Python Code)

Max Activating Token Index: 740

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1612536 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0266. Min Act: -0.0000

Data Index: 203949 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0247. Min Act: -0.0000

Data Index: 644388 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1026295 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0233. Min Act: -0.0000

Data Index: 347114 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0250. Min Act: -0.0000

Data Index: 561188 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1062198 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0273. Min Act: -0.0000

Data Index: 784999 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0224. Min Act: -0.0000

Data Index: 812679 (C4 (Web Text))

Max Activating Token Index: 766