Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 233 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1825. Min Act: -0.0001

Data Index: 93326 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1710. Min Act: -0.0001

Data Index: 898946 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1587. Min Act: -0.0001

Data Index: 204825 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1513. Min Act: -0.0001

Data Index: 484509 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1390. Min Act: -0.0001

Data Index: 592924 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1394. Min Act: -0.0001

Data Index: 390010 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1438. Min Act: -0.0001

Data Index: 425912 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1424. Min Act: -0.0001

Data Index: 713363 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1362. Min Act: -0.0001

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1376. Min Act: -0.0001

Data Index: 384236 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1328. Min Act: -0.0001

Data Index: 176072 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1321. Min Act: -0.0001

Data Index: 363998 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1272. Min Act: -0.0001

Data Index: 664731 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1237196 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1312. Min Act: -0.0001

Data Index: 932599 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1260. Min Act: -0.0001

Data Index: 631537 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1297. Min Act: -0.0001

Data Index: 622777 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1031410 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1295. Min Act: -0.0001

Data Index: 644339 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.1825. Min Range: -0.1825

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1218412 (C4 (Web Text))

Max Activating Token Index: 221