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

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

Neuron 614 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: 2.8628. Min Range: -2.8628

Max Act: 2.8628. Min Act: -0.0000

Data Index: 1160000 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.5946. Min Act: -0.0000

Data Index: 625495 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.4640. Min Act: -0.0000

Data Index: 193418 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.3387. Min Act: -0.0000

Data Index: 1307253 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.3955. Min Act: -0.0000

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.3464. Min Act: -0.0000

Data Index: 984366 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.3234. Min Act: -0.0000

Data Index: 335845 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.1941. Min Act: -0.0000

Data Index: 1010273 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.1639. Min Act: -0.0000

Data Index: 320958 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.3629. Min Act: -0.0000

Data Index: 200447 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.2091. Min Act: -0.0000

Data Index: 1155870 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.2123. Min Act: -0.0000

Data Index: 306599 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.2004. Min Act: -0.0000

Data Index: 54370 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.1946. Min Act: -0.0000

Data Index: 903509 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.8628. Min Range: -2.8628

Max Act: 1.9455. Min Act: -0.0000

Data Index: 70481 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.1340. Min Act: -0.0000

Data Index: 1257587 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.1385. Min Act: -0.0000

Data Index: 663399 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.2402. Min Act: -0.0000

Data Index: 588630 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.0768. Min Act: -0.0000

Data Index: 89096 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.8628. Min Range: -2.8628

Max Act: 2.0839. Min Act: -0.0000

Data Index: 495618 (C4 (Web Text))

Max Activating Token Index: 556