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

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

Neuron 5880 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: 2.0002. Min Range: -2.0002

Max Act: 2.0002. Min Act: -0.0000

Data Index: 934260 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.7625. Min Act: -0.0000

Data Index: 169515 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1243487 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.6575. Min Act: -0.0000

Data Index: 368819 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1263235 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.5176. Min Act: -0.0000

Data Index: 845370 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.5056. Min Act: -0.0000

Data Index: 84639 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.5778. Min Act: -0.0000

Data Index: 475777 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1064417 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4279. Min Act: -0.0000

Data Index: 1301048 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4382. Min Act: -0.0000

Data Index: 52373 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.5212. Min Act: -0.0000

Data Index: 496432 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4543. Min Act: -0.0000

Data Index: 840250 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4069. Min Act: -0.0000

Data Index: 1278656 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1280946 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1489. Min Act: -0.0000

Data Index: 224835 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3748. Min Act: -0.0000

Data Index: 433263 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3784. Min Act: -0.0000

Data Index: 83026 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3649. Min Act: -0.0000

Data Index: 684641 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3680. Min Act: -0.0000

Data Index: 471685 (C4 (Web Text))

Max Activating Token Index: 1016