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

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

Neuron 763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0001

Data Index: 683672 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0593. Min Act: -0.0001

Data Index: 471874 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0552. Min Act: -0.0001

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0537. Min Act: -0.0001

Data Index: 433968 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0525. Min Act: -0.0001

Data Index: 835318 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0461. Min Act: -0.0001

Data Index: 991875 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0499. Min Act: -0.0001

Data Index: 503290 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0465. Min Act: -0.0001

Data Index: 883211 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1591601 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0441. Min Act: -0.0001

Data Index: 710826 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0421. Min Act: -0.0002

Data Index: 658647 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1067234 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0390. Min Act: -0.0001

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0402. Min Act: -0.0002

Data Index: 190906 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0353. Min Act: -0.0001

Data Index: 541436 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0351. Min Act: -0.0001

Data Index: 1517561 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0348. Min Act: -0.0001

Data Index: 624165 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0321. Min Act: -0.0002

Data Index: 914889 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1533819 (Python Code)

Max Activating Token Index: 461