Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7861. Min Act: -0.0003

Data Index: 1111491 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7528. Min Act: -0.0003

Data Index: 909888 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7774. Min Act: -0.0003

Data Index: 1053111 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6580. Min Act: -0.0003

Data Index: 632869 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.7002. Min Act: -0.0003

Data Index: 1248063 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6914. Min Act: -0.0003

Data Index: 1266160 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6709. Min Act: -0.0003

Data Index: 559341 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6275. Min Act: -0.0003

Data Index: 1238990 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6204. Min Act: -0.0003

Data Index: 1279291 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6774. Min Act: -0.0003

Data Index: 942975 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6359. Min Act: -0.0003

Data Index: 1115539 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6336. Min Act: -0.0003

Data Index: 845184 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5700. Min Act: -0.0003

Data Index: 43643 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6613. Min Act: -0.0003

Data Index: 437474 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6317. Min Act: -0.0003

Data Index: 978698 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6258. Min Act: -0.0003

Data Index: 1065 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6316. Min Act: -0.0003

Data Index: 406659 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.5341. Min Act: -0.0003

Data Index: 154953 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6243. Min Act: -0.0003

Data Index: 801670 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.7861. Min Range: -0.7861

Max Act: 0.6585. Min Act: -0.0003

Data Index: 994641 (C4 (Web Text))

Max Activating Token Index: 456