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

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

Neuron 3721 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.2259. Min Act: -0.0000

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1569. Min Act: -0.0000

Data Index: 56191 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1545. Min Act: -0.0000

Data Index: 802868 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1471. Min Act: -0.0000

Data Index: 633429 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1517. Min Act: -0.0000

Data Index: 183832 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1463. Min Act: -0.0000

Data Index: 57891 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1348. Min Act: -0.0000

Data Index: 55368 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1335. Min Act: -0.0000

Data Index: 502288 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1263508 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1255179 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1273. Min Act: -0.0000

Data Index: 709489 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1383. Min Act: -0.0000

Data Index: 303797 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1288. Min Act: -0.0000

Data Index: 718523 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1272. Min Act: -0.0000

Data Index: 127113 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1295. Min Act: -0.0000

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1241. Min Act: -0.0000

Data Index: 146962 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1262. Min Act: -0.0000

Data Index: 335902 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1223. Min Act: -0.0000

Data Index: 641753 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1258. Min Act: -0.0000

Data Index: 645773 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.2259. Min Range: -0.2259

Max Act: 0.1221. Min Act: -0.0000

Data Index: 879583 (C4 (Web Text))

Max Activating Token Index: 498