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

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

Neuron 919 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: 0.7865. Min Range: -0.7865

Max Act: 0.7865. Min Act: -0.0001

Data Index: 1016706 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.7650. Min Act: -0.0001

Data Index: 590378 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.7084. Min Act: -0.0001

Data Index: 305004 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6839. Min Act: -0.0001

Data Index: 116937 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6588. Min Act: -0.0001

Data Index: 448893 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.7220. Min Act: -0.0001

Data Index: 716433 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6614. Min Act: -0.0001

Data Index: 687611 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6377. Min Act: -0.0001

Data Index: 421065 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6162. Min Act: -0.0000

Data Index: 971734 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6535. Min Act: -0.0001

Data Index: 339314 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6135. Min Act: -0.0001

Data Index: 940592 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6709. Min Act: -0.0001

Data Index: 351607 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6356. Min Act: -0.0001

Data Index: 313190 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6372. Min Act: -0.0001

Data Index: 780727 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6147. Min Act: -0.0001

Data Index: 197475 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6388. Min Act: -0.0001

Data Index: 674861 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1051327 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.5978. Min Act: -0.0001

Data Index: 1105009 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6346. Min Act: -0.0001

Data Index: 13738 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.7865. Min Range: -0.7865

Max Act: 0.6535. Min Act: -0.0000

Data Index: 696022 (C4 (Web Text))

Max Activating Token Index: 641