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

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

Neuron 417 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1079. Min Range: -1.1079

Max Act: 1.1079. Min Act: -0.0001

Data Index: 1071747 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8399. Min Act: -0.0001

Data Index: 1265355 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1347046 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7123. Min Act: -0.0001

Data Index: 479343 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1002216 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7492. Min Act: -0.0001

Data Index: 343298 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6712. Min Act: -0.0001

Data Index: 355807 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6980. Min Act: -0.0001

Data Index: 552974 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6826. Min Act: -0.0001

Data Index: 90588 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.7047. Min Act: -0.0001

Data Index: 1165522 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6265. Min Act: -0.0001

Data Index: 912896 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6253. Min Act: -0.0001

Data Index: 255504 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6622. Min Act: -0.0001

Data Index: 177610 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6369. Min Act: -0.0001

Data Index: 51247 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1100935 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1493163 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6506. Min Act: -0.0001

Data Index: 1147660 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6270. Min Act: -0.0001

Data Index: 518168 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6496. Min Act: -0.0001

Data Index: 473548 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.1079. Min Range: -1.1079

Max Act: 0.6079. Min Act: -0.0001

Data Index: 312583 (C4 (Web Text))

Max Activating Token Index: 348