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

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

Neuron 676 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0000

Data Index: 7704 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1629. Min Act: -0.0001

Data Index: 912277 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1628. Min Act: -0.0001

Data Index: 49 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1572. Min Act: -0.0001

Data Index: 566191 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1391. Min Act: -0.0001

Data Index: 1300359 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1489. Min Act: -0.0000

Data Index: 952609 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1467. Min Act: -0.0000

Data Index: 304369 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1457. Min Act: -0.0000

Data Index: 320523 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1445. Min Act: -0.0001

Data Index: 197241 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1426. Min Act: -0.0000

Data Index: 457815 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1181796 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1372. Min Act: -0.0000

Data Index: 604260 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1423. Min Act: -0.0001

Data Index: 825369 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1301. Min Act: -0.0001

Data Index: 484081 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1406. Min Act: -0.0001

Data Index: 18510 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1342. Min Act: -0.0000

Data Index: 19255 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1374. Min Act: -0.0001

Data Index: 253928 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1420. Min Act: -0.0001

Data Index: 429069 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1272. Min Act: -0.0001

Data Index: 767169 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1366. Min Act: -0.0000

Data Index: 520607 (C4 (Web Text))

Max Activating Token Index: 543