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

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

Neuron 5011 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: 2.4190. Min Range: -2.4190

Max Act: 2.4190. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 2.4190. Min Range: -2.4190

Max Act: 2.2456. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.6351. Min Act: -0.0000

Data Index: 32052 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.5464. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.5269. Min Act: -0.0000

Data Index: 797284 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.3660. Min Act: 0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.3734. Min Act: -0.0000

Data Index: 1379292 (Python Code)

Max Activating Token Index: 554

Text #8

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.2284. Min Act: -0.0000

Data Index: 44342 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.2394. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.1892. Min Act: 0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.1374. Min Act: 0.0000

Data Index: 1590360 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.1003. Min Act: -0.0000

Data Index: 805170 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1436778 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 2.4190. Min Range: -2.4190

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1502016 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 2.4190. Min Range: -2.4190

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1348552 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 2.4190. Min Range: -2.4190

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1501862 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 2.4190. Min Range: -2.4190

Max Act: 0.9637. Min Act: -0.0000

Data Index: 112432 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 2.4190. Min Range: -2.4190

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1412721 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 2.4190. Min Range: -2.4190

Max Act: 0.8680. Min Act: 0.0000

Data Index: 757353 (C4 (Web Text))

Max Activating Token Index: 663