Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 772 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4441. Min Range: -4.4441

Max Act: 4.4441. Min Act: -0.0000

Data Index: 152963 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.3715. Min Act: -0.0000

Data Index: 181236 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.3428. Min Act: -0.0000

Data Index: 500740 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.8971. Min Act: -0.0000

Data Index: 189235 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.3564. Min Act: -0.0000

Data Index: 1138309 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.0094. Min Act: -0.0000

Data Index: 748718 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.1015. Min Act: -0.0000

Data Index: 247565 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.0679. Min Act: -0.0000

Data Index: 509452 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.0619. Min Act: -0.0000

Data Index: 285649 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.0696. Min Act: -0.0000

Data Index: 1059531 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.8213. Min Act: -0.0000

Data Index: 831746 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.2091. Min Act: -0.0000

Data Index: 302732 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 4.4441. Min Range: -4.4441

Max Act: 3.1783. Min Act: -0.0000

Data Index: 971581 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.6119. Min Act: -0.0000

Data Index: 1083312 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.9622. Min Act: -0.0000

Data Index: 1186998 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.9541. Min Act: -0.0000

Data Index: 1205667 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.8037. Min Act: -0.0000

Data Index: 787375 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.7194. Min Act: -0.0001

Data Index: 491825 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.9071. Min Act: -0.0000

Data Index: 223486 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 4.4441. Min Range: -4.4441

Max Act: 2.6284. Min Act: -0.0000

Data Index: 385815 (C4 (Web Text))

Max Activating Token Index: 702