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

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

Neuron 4053 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1842. Min Act: -0.0002

Data Index: 775060 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1700. Min Act: -0.0002

Data Index: 94611 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1617. Min Act: -0.0002

Data Index: 658017 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1488. Min Act: -0.0002

Data Index: 217879 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1496. Min Act: -0.0002

Data Index: 1111741 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1441. Min Act: -0.0002

Data Index: 62433 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1471. Min Act: -0.0002

Data Index: 156272 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1400. Min Act: -0.0002

Data Index: 1153852 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1476. Min Act: -0.0002

Data Index: 133203 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1352. Min Act: -0.0002

Data Index: 344073 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1389. Min Act: -0.0002

Data Index: 1227540 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1374. Min Act: -0.0002

Data Index: 566279 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1334. Min Act: -0.0002

Data Index: 937680 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1227529 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1369. Min Act: -0.0002

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1394. Min Act: -0.0002

Data Index: 488495 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1270041 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1355. Min Act: -0.0002

Data Index: 908168 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1335. Min Act: -0.0002

Data Index: 467941 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1349. Min Act: -0.0002

Data Index: 463921 (C4 (Web Text))

Max Activating Token Index: 782