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

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

Neuron 4963 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9491. Min Range: -4.9491

Max Act: 4.9491. Min Act: -0.0000

Data Index: 919074 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 4.9491. Min Range: -4.9491

Max Act: 4.5241. Min Act: -0.0000

Data Index: 391419 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.9242. Min Act: -0.0000

Data Index: 119209 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.7612. Min Act: -0.0000

Data Index: 1243645 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.0773. Min Act: -0.0000

Data Index: 244170 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.2414. Min Act: -0.0000

Data Index: 223530 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.1634. Min Act: -0.0000

Data Index: 463950 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.9409. Min Act: -0.0000

Data Index: 749077 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.1800. Min Act: -0.0000

Data Index: 919999 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.8400. Min Act: -0.0000

Data Index: 196198 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.9500. Min Act: -0.0000

Data Index: 845743 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 4.9491. Min Range: -4.9491

Max Act: 3.0918. Min Act: -0.0000

Data Index: 79434 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.7483. Min Act: -0.0000

Data Index: 768844 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.8743. Min Act: -0.0000

Data Index: 333948 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.8594. Min Act: -0.0000

Data Index: 1019880 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.8331. Min Act: -0.0000

Data Index: 767528 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.8077. Min Act: -0.0000

Data Index: 1109206 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.9169. Min Act: -0.0000

Data Index: 797611 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.9247. Min Act: -0.0000

Data Index: 138271 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 4.9491. Min Range: -4.9491

Max Act: 2.5622. Min Act: -0.0000

Data Index: 940659 (C4 (Web Text))

Max Activating Token Index: 376