Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4704 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3375. Min Range: -2.3375

Max Act: 2.3375. Min Act: -0.0000

Data Index: 1357586 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.8942. Min Act: -0.0000

Data Index: 1230026 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.7552. Min Act: -0.0000

Data Index: 306882 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.7108. Min Act: -0.0000

Data Index: 628183 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1270372 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.7121. Min Act: -0.0000

Data Index: 747904 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6808. Min Act: -0.0000

Data Index: 218003 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6882. Min Act: -0.0000

Data Index: 939685 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6372. Min Act: -0.0000

Data Index: 1114205 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6132. Min Act: -0.0000

Data Index: 572568 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6092. Min Act: -0.0000

Data Index: 413738 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5142. Min Act: -0.0000

Data Index: 84240 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.6525. Min Act: -0.0000

Data Index: 548372 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5993. Min Act: -0.0000

Data Index: 392486 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5960. Min Act: -0.0000

Data Index: 534190 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5440. Min Act: -0.0000

Data Index: 1210382 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5385. Min Act: -0.0000

Data Index: 954950 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5500. Min Act: -0.0000

Data Index: 333793 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5055. Min Act: -0.0000

Data Index: 693456 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 2.3375. Min Range: -2.3375

Max Act: 1.5006. Min Act: -0.0000

Data Index: 234271 (C4 (Web Text))

Max Activating Token Index: 891