Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3352 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.9326. Min Act: -0.0002

Data Index: 258858 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.8743. Min Act: -0.0002

Data Index: 445616 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.8577. Min Act: -0.0002

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7950. Min Act: -0.0002

Data Index: 883730 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.8096. Min Act: -0.0002

Data Index: 533679 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7935. Min Act: -0.0002

Data Index: 13756 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7256. Min Act: -0.0002

Data Index: 918328 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7896. Min Act: -0.0002

Data Index: 1267966 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.8024. Min Act: -0.0002

Data Index: 926538 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7537. Min Act: -0.0002

Data Index: 884225 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7102. Min Act: -0.0002

Data Index: 1261676 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7294. Min Act: -0.0002

Data Index: 1237850 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7582. Min Act: -0.0002

Data Index: 11462 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6481. Min Act: -0.0002

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.7056. Min Act: -0.0002

Data Index: 604847 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6865. Min Act: -0.0002

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6717. Min Act: -0.0002

Data Index: 1103166 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6538. Min Act: -0.0002

Data Index: 71374 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6180. Min Act: -0.0002

Data Index: 358601 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.9326. Min Range: -1.9326

Max Act: 1.6036. Min Act: -0.0002

Data Index: 1177396 (C4 (Web Text))

Max Activating Token Index: 290