Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1676 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3640. Min Act: -0.0001

Data Index: 774328 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3869. Min Act: -0.0001

Data Index: 853648 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3726. Min Act: -0.0001

Data Index: 581496 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1326643 (C4 (Web Text))

Max Activating Token Index: 324

Text #4

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3511. Min Act: -0.0001

Data Index: 326577 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3448. Min Act: -0.0001

Data Index: 900002 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3654. Min Act: -0.0001

Data Index: 842975 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3503. Min Act: -0.0001

Data Index: 405811 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1274800 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3494. Min Act: -0.0001

Data Index: 288554 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3392. Min Act: -0.0001

Data Index: 759565 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3457. Min Act: -0.0001

Data Index: 802431 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3337. Min Act: -0.0001

Data Index: 1064989 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3309. Min Act: -0.0001

Data Index: 232379 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1206006 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3295. Min Act: -0.0001

Data Index: 580168 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3308. Min Act: -0.0001

Data Index: 103276 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3270. Min Act: -0.0001

Data Index: 493534 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1316438 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.3869. Min Range: -0.3869

Max Act: 0.3364. Min Act: -0.0001

Data Index: 1260292 (C4 (Web Text))

Max Activating Token Index: 173