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

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

Neuron 3634 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1433. Min Act: -0.0002

Data Index: 861680 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1289125 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1354638 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1327. Min Act: -0.0001

Data Index: 441421 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1457. Min Act: -0.0002

Data Index: 148972 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1257206 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1372. Min Act: -0.0001

Data Index: 1267245 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1351842 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1287. Min Act: -0.0001

Data Index: 543738 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1406. Min Act: -0.0002

Data Index: 1063923 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1129933 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1187788 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1129357 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1279. Min Act: -0.0001

Data Index: 155037 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1324. Min Act: -0.0002

Data Index: 257342 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1176685 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1320124 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1336789 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1295. Min Act: -0.0001

Data Index: 330060 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1311. Min Act: -0.0001

Data Index: 97950 (C4 (Web Text))

Max Activating Token Index: 456