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

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

Neuron 1947 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.6067. Min Act: -0.0000

Data Index: 650917 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.7176. Min Act: -0.0000

Data Index: 613929 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.3908. Min Act: -0.0000

Data Index: 663067 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.0574. Min Act: -0.0000

Data Index: 461186 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.7095. Min Act: -0.0000

Data Index: 1195449 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.2001. Min Act: -0.0000

Data Index: 869591 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.0969. Min Act: -0.0000

Data Index: 321335 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.0703. Min Act: -0.0000

Data Index: 106407 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 6.7176. Min Range: -6.7176

Max Act: 6.0270. Min Act: -0.0000

Data Index: 1298525 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.5489. Min Act: -0.0000

Data Index: 663648 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.7351. Min Act: -0.0000

Data Index: 1355918 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.2930. Min Act: -0.0000

Data Index: 391591 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.5729. Min Act: -0.0000

Data Index: 799787 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.2853. Min Act: -0.0000

Data Index: 1082739 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.1783. Min Act: -0.0000

Data Index: 1128113 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.3262. Min Act: -0.0000

Data Index: 588931 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.4783. Min Act: -0.0000

Data Index: 143880 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.3984. Min Act: -0.0000

Data Index: 938728 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.1695. Min Act: -0.0000

Data Index: 440486 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 6.7176. Min Range: -6.7176

Max Act: 5.3484. Min Act: -0.0000

Data Index: 267103 (C4 (Web Text))

Max Activating Token Index: 91