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

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

Neuron 4434 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.9702. Min Act: -0.0000

Data Index: 321659 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.5945. Min Act: -0.0000

Data Index: 1130947 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.7153. Min Act: -0.0000

Data Index: 1308231 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.5679. Min Act: -0.0000

Data Index: 49852 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.6743. Min Act: -0.0000

Data Index: 1024078 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.6747. Min Act: -0.0000

Data Index: 432944 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.5235. Min Act: -0.0000

Data Index: 475448 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.5154. Min Act: -0.0000

Data Index: 1503916 (Python Code)

Max Activating Token Index: 493

Text #8

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.4236. Min Act: -0.0000

Data Index: 1329938 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2952. Min Act: -0.0000

Data Index: 380850 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.5966. Min Act: -0.0000

Data Index: 371176 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.3453. Min Act: -0.0000

Data Index: 1152723 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.3294. Min Act: -0.0000

Data Index: 604196 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.1399. Min Act: -0.0000

Data Index: 42435 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2582. Min Act: -0.0000

Data Index: 1340018 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2427. Min Act: -0.0000

Data Index: 802003 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2280. Min Act: -0.0000

Data Index: 914972 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2198. Min Act: -0.0000

Data Index: 564050 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.1976. Min Act: -0.0000

Data Index: 595219 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2019. Min Act: -0.0000

Data Index: 1524579 (Python Code)

Max Activating Token Index: 84