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

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

Neuron 1654 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: 0.2136. Min Range: -0.2136

Max Act: 0.2136. Min Act: -0.0001

Data Index: 864699 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1181913 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.2089. Min Act: -0.0001

Data Index: 335998 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1026310 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1735. Min Act: -0.0001

Data Index: 975631 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1950. Min Act: -0.0000

Data Index: 243913 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1604. Min Act: -0.0001

Data Index: 370060 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1609. Min Act: -0.0001

Data Index: 590631 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1648. Min Act: -0.0001

Data Index: 223191 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1345. Min Act: -0.0000

Data Index: 719324 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1089069 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1515. Min Act: -0.0001

Data Index: 579467 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1550. Min Act: -0.0001

Data Index: 988266 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1209049 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1440. Min Act: -0.0001

Data Index: 890168 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1477. Min Act: -0.0001

Data Index: 880365 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1124043 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1413. Min Act: -0.0000

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1411. Min Act: -0.0001

Data Index: 144030 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.2136. Min Range: -0.2136

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1295108 (C4 (Web Text))

Max Activating Token Index: 685