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

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

Neuron 1825 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1361283 (Python Code)

Max Activating Token Index: 140

Text #1

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1434749 (Python Code)

Max Activating Token Index: 164

Text #2

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1526917 (Python Code)

Max Activating Token Index: 375

Text #3

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1414270 (Python Code)

Max Activating Token Index: 140

Text #4

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1477. Min Act: -0.0001

Data Index: 1221191 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1573620 (Python Code)

Max Activating Token Index: 605

Text #6

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1463808 (Python Code)

Max Activating Token Index: 702

Text #7

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1419. Min Act: -0.0001

Data Index: 199436 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1097128 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1419. Min Act: -0.0001

Data Index: 922141 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1380907 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1566072 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1402069 (Python Code)

Max Activating Token Index: 489

Text #13

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1278. Min Act: -0.0001

Data Index: 438343 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1623775 (Python Code)

Max Activating Token Index: 151

Text #15

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1201762 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1615520 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1408285 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1213. Min Act: -0.0001

Data Index: 563138 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.1587. Min Range: -0.1587

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1640829 (Python Code)

Max Activating Token Index: 46