Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1212 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0006

Data Index: 775940 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0405. Min Act: -0.0006

Data Index: 632591 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0366. Min Act: -0.0006

Data Index: 337355 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0357. Min Act: -0.0006

Data Index: 294545 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0364. Min Act: -0.0006

Data Index: 99465 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0354. Min Act: -0.0006

Data Index: 808344 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0348. Min Act: -0.0006

Data Index: 1189069 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0337. Min Act: -0.0006

Data Index: 586799 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0329. Min Act: -0.0006

Data Index: 1062948 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0323. Min Act: -0.0006

Data Index: 101283 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0312. Min Act: -0.0006

Data Index: 424467 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1183969 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0299. Min Act: -0.0006

Data Index: 685600 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0289. Min Act: -0.0006

Data Index: 745634 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0282. Min Act: -0.0006

Data Index: 66976 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1225569 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0285. Min Act: -0.0006

Data Index: 751205 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1172947 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0269. Min Act: -0.0006

Data Index: 840860 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0261. Min Act: -0.0006

Data Index: 441179 (C4 (Web Text))

Max Activating Token Index: 853