Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1827. Min Act: -0.0000

Data Index: 750276 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1683. Min Act: -0.0000

Data Index: 488830 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1420. Min Act: -0.0000

Data Index: 841915 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1353645 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1494. Min Act: -0.0000

Data Index: 237900 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1526. Min Act: -0.0000

Data Index: 7787 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1444. Min Act: -0.0000

Data Index: 970474 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1313. Min Act: -0.0000

Data Index: 1120819 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1339. Min Act: -0.0000

Data Index: 904916 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1364. Min Act: -0.0000

Data Index: 79578 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1308320 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1040407 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1292. Min Act: -0.0000

Data Index: 933483 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1212. Min Act: -0.0000

Data Index: 875943 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1258. Min Act: -0.0000

Data Index: 812271 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1341516 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1384. Min Act: -0.0000

Data Index: 838800 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1332. Min Act: -0.0000

Data Index: 657768 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1109. Min Act: -0.0000

Data Index: 125316 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.1827. Min Range: -0.1827

Max Act: 0.1323. Min Act: -0.0000

Data Index: 630251 (C4 (Web Text))

Max Activating Token Index: 292