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

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

Neuron 5950 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: 3.1675. Min Range: -3.1675

Max Act: 3.0241. Min Act: -0.0000

Data Index: 616361 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.9053. Min Act: -0.0000

Data Index: 24265 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 3.1675. Min Range: -3.1675

Max Act: 3.1145. Min Act: -0.0000

Data Index: 330480 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.9515. Min Act: -0.0000

Data Index: 1358937 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.1675. Min Range: -3.1675

Max Act: 3.1675. Min Act: -0.0000

Data Index: 510623 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.9101. Min Act: -0.0000

Data Index: 760580 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.8435. Min Act: -0.0000

Data Index: 246594 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.9470. Min Act: -0.0000

Data Index: 757305 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.8109. Min Act: -0.0000

Data Index: 1283995 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.8170. Min Act: -0.0000

Data Index: 440457 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.9062. Min Act: -0.0000

Data Index: 71893 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.8856. Min Act: -0.0000

Data Index: 1215033 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.6360. Min Act: -0.0000

Data Index: 845456 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.7525. Min Act: -0.0000

Data Index: 533770 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.6169. Min Act: -0.0000

Data Index: 863830 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.6031. Min Act: -0.0000

Data Index: 254146 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.6903. Min Act: -0.0000

Data Index: 173485 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.6935. Min Act: -0.0000

Data Index: 32071 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.5622. Min Act: -0.0000

Data Index: 139924 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 3.1675. Min Range: -3.1675

Max Act: 2.3010. Min Act: -0.0000

Data Index: 462313 (C4 (Web Text))

Max Activating Token Index: 643