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

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

Neuron 777 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: 1.4800. Min Range: -1.4800

Max Act: 1.4800. Min Act: -0.0001

Data Index: 216417 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.4464. Min Act: -0.0001

Data Index: 1148268 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.3413. Min Act: -0.0001

Data Index: 406638 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.3880. Min Act: -0.0001

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.3037. Min Act: -0.0001

Data Index: 739200 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2237. Min Act: -0.0001

Data Index: 374150 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2787. Min Act: -0.0001

Data Index: 859183 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2556. Min Act: -0.0001

Data Index: 788559 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2317. Min Act: -0.0001

Data Index: 720517 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2417. Min Act: -0.0001

Data Index: 840310 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2712. Min Act: -0.0001

Data Index: 248831 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2089. Min Act: -0.0001

Data Index: 1250716 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1310904 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2695. Min Act: -0.0001

Data Index: 518869 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.2159. Min Act: -0.0001

Data Index: 676074 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.0755. Min Act: -0.0001

Data Index: 907964 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1394. Min Act: -0.0001

Data Index: 561852 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1306. Min Act: -0.0001

Data Index: 1157565 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1728. Min Act: -0.0001

Data Index: 645604 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 1.4800. Min Range: -1.4800

Max Act: 1.1517. Min Act: -0.0001

Data Index: 824714 (C4 (Web Text))

Max Activating Token Index: 570