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

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

Neuron 2756 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6434. Min Range: -2.6434

Max Act: 2.6434. Min Act: -0.0000

Data Index: 1206611 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 2.6434. Min Range: -2.6434

Max Act: 2.5021. Min Act: -0.0000

Data Index: 288489 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 2.6434. Min Range: -2.6434

Max Act: 2.1983. Min Act: -0.0000

Data Index: 1193284 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.6434. Min Range: -2.6434

Max Act: 2.1942. Min Act: -0.0000

Data Index: 876605 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.8344. Min Act: -0.0000

Data Index: 593271 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.7884. Min Act: -0.0000

Data Index: 88032 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.6597. Min Act: -0.0000

Data Index: 812592 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.8169. Min Act: -0.0000

Data Index: 237508 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.6283. Min Act: -0.0000

Data Index: 220928 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.9582. Min Act: -0.0000

Data Index: 196799 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.6284. Min Act: -0.0000

Data Index: 874539 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.4990. Min Act: -0.0000

Data Index: 85398 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.5862. Min Act: -0.0000

Data Index: 850523 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1251549 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.3912. Min Act: -0.0000

Data Index: 651731 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.6181. Min Act: -0.0000

Data Index: 198183 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1367267 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1515376 (Python Code)

Max Activating Token Index: 414

Text #18

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.4923. Min Act: -0.0000

Data Index: 6323 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 2.6434. Min Range: -2.6434

Max Act: 1.4617. Min Act: -0.0000

Data Index: 927346 (C4 (Web Text))

Max Activating Token Index: 402