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

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

Neuron 507 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: 10.5293. Min Range: -10.5293

Max Act: 10.4036. Min Act: -0.0000

Data Index: 776050 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 10.5293. Min Range: -10.5293

Max Act: 10.5293. Min Act: -0.0000

Data Index: 1005389 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 10.5293. Min Range: -10.5293

Max Act: 7.1142. Min Act: -0.0000

Data Index: 654435 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 10.5293. Min Range: -10.5293

Max Act: 8.4390. Min Act: -0.0000

Data Index: 1223304 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 10.5293. Min Range: -10.5293

Max Act: 6.5880. Min Act: -0.0000

Data Index: 307059 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.2650. Min Act: -0.0000

Data Index: 997284 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 10.5293. Min Range: -10.5293

Max Act: 1.2432. Min Act: -0.0000

Data Index: 856862 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1428452 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 10.5293. Min Range: -10.5293

Max Act: 2.2297. Min Act: -0.0000

Data Index: 76384 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.3141. Min Act: -0.0000

Data Index: 897824 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.3646. Min Act: -0.0001

Data Index: 1364295 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.2504. Min Act: -0.0001

Data Index: 861840 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.2153. Min Act: -0.0000

Data Index: 474398 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1555341 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.1826. Min Act: -0.0000

Data Index: 332921 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.1687. Min Act: -0.0000

Data Index: 439043 (C4 (Web Text))

Max Activating Token Index: 417

Text #16

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.1688. Min Act: -0.0000

Data Index: 521096 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.1691. Min Act: -0.0000

Data Index: 299899 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.1589. Min Act: -0.0000

Data Index: 496488 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 10.5293. Min Range: -10.5293

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1247691 (C4 (Web Text))

Max Activating Token Index: 329