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

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

Neuron 2597 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1080058 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.4012. Min Act: -0.0000

Data Index: 725637 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1225726 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3758. Min Act: -0.0001

Data Index: 130430 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3721. Min Act: -0.0000

Data Index: 614328 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1256611 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1079770 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3400. Min Act: -0.0001

Data Index: 349091 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3356. Min Act: -0.0000

Data Index: 221291 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1127903 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3298. Min Act: -0.0001

Data Index: 182442 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3198. Min Act: -0.0000

Data Index: 738059 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3081. Min Act: -0.0000

Data Index: 297444 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3287. Min Act: -0.0000

Data Index: 373107 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3249. Min Act: -0.0000

Data Index: 171696 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3109. Min Act: -0.0001

Data Index: 477639 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3078. Min Act: -0.0000

Data Index: 592578 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1241802 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.3175. Min Act: -0.0000

Data Index: 693491 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.4617. Min Range: -0.4617

Max Act: 0.2994. Min Act: -0.0000

Data Index: 95818 (C4 (Web Text))

Max Activating Token Index: 250