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

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

Neuron 3714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6829. Min Act: -0.0001

Data Index: 60494 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6044. Min Act: -0.0001

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4228. Min Act: -0.0002

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5550. Min Act: -0.0001

Data Index: 825229 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5165. Min Act: -0.0002

Data Index: 294195 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4691. Min Act: -0.0001

Data Index: 1162227 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5201. Min Act: -0.0001

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4855. Min Act: -0.0001

Data Index: 244641 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4788. Min Act: -0.0001

Data Index: 995156 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5105. Min Act: -0.0002

Data Index: 450480 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4223. Min Act: -0.0002

Data Index: 793720 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4350. Min Act: -0.0001

Data Index: 1351115 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4158. Min Act: -0.0001

Data Index: 378072 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.3923. Min Act: -0.0001

Data Index: 496039 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4216. Min Act: -0.0001

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.3051. Min Act: -0.0001

Data Index: 843776 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1194629 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.3555. Min Act: -0.0002

Data Index: 559175 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.3507. Min Act: -0.0001

Data Index: 846664 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.3496. Min Act: -0.0001

Data Index: 103306 (C4 (Web Text))

Max Activating Token Index: 509