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

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

Neuron 2706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1768. Min Act: -0.0001

Data Index: 6894 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1655. Min Act: -0.0000

Data Index: 579257 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1625. Min Act: -0.0001

Data Index: 391091 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1626. Min Act: -0.0001

Data Index: 90162 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1267002 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1093930 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1664. Min Act: -0.0001

Data Index: 120330 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1427. Min Act: -0.0001

Data Index: 741779 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1413. Min Act: -0.0001

Data Index: 26115 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1450. Min Act: -0.0000

Data Index: 799248 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1342. Min Act: -0.0000

Data Index: 1291441 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1438. Min Act: -0.0001

Data Index: 8834 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1339181 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1277. Min Act: -0.0001

Data Index: 532671 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1007559 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1315. Min Act: -0.0001

Data Index: 683894 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1336. Min Act: -0.0000

Data Index: 755689 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1296. Min Act: -0.0001

Data Index: 72131 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1372. Min Act: -0.0001

Data Index: 6085 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.1768. Min Range: -0.1768

Max Act: 0.1263. Min Act: -0.0001

Data Index: 360740 (C4 (Web Text))

Max Activating Token Index: 470