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

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

Neuron 3477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6974. Min Act: -0.0000

Data Index: 720833 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.7275. Min Act: -0.0000

Data Index: 483540 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6335. Min Act: -0.0000

Data Index: 503886 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5844. Min Act: -0.0001

Data Index: 200124 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1254709 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5434. Min Act: -0.0001

Data Index: 705613 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5230. Min Act: -0.0000

Data Index: 42084 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5385. Min Act: -0.0000

Data Index: 938048 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5348. Min Act: -0.0000

Data Index: 760679 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4925. Min Act: -0.0000

Data Index: 653692 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1102075 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4821. Min Act: -0.0001

Data Index: 265708 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4925. Min Act: -0.0001

Data Index: 1211084 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5205. Min Act: -0.0000

Data Index: 290229 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5154. Min Act: -0.0001

Data Index: 273260 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1109040 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1286814 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1075899 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4768. Min Act: -0.0000

Data Index: 481025 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.4606. Min Act: -0.0001

Data Index: 192926 (C4 (Web Text))

Max Activating Token Index: 599