Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4715 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.9204. Min Act: -0.0000

Data Index: 262510 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.9050. Min Act: -0.0000

Data Index: 924844 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.8588. Min Act: -0.0000

Data Index: 362966 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1040858 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.9026. Min Act: -0.0000

Data Index: 615589 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1125877 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.8357. Min Act: -0.0000

Data Index: 738200 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7749. Min Act: -0.0000

Data Index: 617505 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7883. Min Act: -0.0000

Data Index: 526211 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7243. Min Act: -0.0000

Data Index: 312264 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7483. Min Act: -0.0000

Data Index: 101646 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6847. Min Act: -0.0000

Data Index: 702545 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7461. Min Act: -0.0000

Data Index: 698958 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7390. Min Act: -0.0000

Data Index: 195684 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7393. Min Act: -0.0000

Data Index: 852730 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.7612. Min Act: -0.0000

Data Index: 648689 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1149480 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1153612 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1291763 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.9204. Min Range: -0.9204

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1095231 (C4 (Web Text))

Max Activating Token Index: 691