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

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

Neuron 4302 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1793. Min Act: -0.0001

Data Index: 762023 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1110. Min Act: -0.0001

Data Index: 463819 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1496. Min Act: -0.0001

Data Index: 948901 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1205095 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1295. Min Act: -0.0001

Data Index: 869731 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1403. Min Act: -0.0001

Data Index: 224954 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1431. Min Act: -0.0001

Data Index: 815705 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1138. Min Act: -0.0001

Data Index: 583544 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1075823 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1230. Min Act: -0.0001

Data Index: 40935 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1197. Min Act: -0.0001

Data Index: 101551 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1101. Min Act: -0.0001

Data Index: 800228 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1180. Min Act: -0.0001

Data Index: 44769 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1194. Min Act: -0.0001

Data Index: 968333 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1224. Min Act: -0.0001

Data Index: 92641 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1182472 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.0984. Min Act: -0.0001

Data Index: 207425 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1154. Min Act: -0.0001

Data Index: 308803 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.0927. Min Act: -0.0001

Data Index: 607409 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.0915. Min Act: -0.0001

Data Index: 680387 (C4 (Web Text))

Max Activating Token Index: 140