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

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

Neuron 771 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: 1.0952. Min Range: -1.0952

Max Act: 1.0952. Min Act: -0.0000

Data Index: 1115 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8652. Min Act: -0.0000

Data Index: 511526 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8808. Min Act: -0.0000

Data Index: 359356 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.9004. Min Act: -0.0000

Data Index: 381095 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8688. Min Act: -0.0000

Data Index: 476524 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8392. Min Act: -0.0000

Data Index: 374539 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8018. Min Act: -0.0000

Data Index: 773917 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1086915 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1240642 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8175. Min Act: -0.0000

Data Index: 649620 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8244. Min Act: -0.0000

Data Index: 227595 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7537. Min Act: -0.0000

Data Index: 1105200 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7790. Min Act: -0.0000

Data Index: 913675 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1323346 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.8110. Min Act: -0.0000

Data Index: 298334 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7810. Min Act: -0.0000

Data Index: 338142 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7734. Min Act: -0.0000

Data Index: 424367 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7709. Min Act: -0.0000

Data Index: 751023 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7146. Min Act: -0.0000

Data Index: 814034 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 1.0952. Min Range: -1.0952

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1279255 (C4 (Web Text))

Max Activating Token Index: 258