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

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

Neuron 32 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0669. Min Range: -1.0669

Max Act: 1.0669. Min Act: -0.0000

Data Index: 101429 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.8836. Min Act: -0.0000

Data Index: 74202 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.8194. Min Act: -0.0000

Data Index: 444093 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.8231. Min Act: -0.0000

Data Index: 346061 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7616. Min Act: -0.0000

Data Index: 20149 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7635. Min Act: -0.0000

Data Index: 270490 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7595. Min Act: -0.0000

Data Index: 447492 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7509. Min Act: -0.0000

Data Index: 757621 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7500. Min Act: -0.0000

Data Index: 468992 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7451. Min Act: -0.0000

Data Index: 6257 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7187. Min Act: -0.0000

Data Index: 42107 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7218. Min Act: -0.0000

Data Index: 280882 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1359308 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7147. Min Act: -0.0000

Data Index: 197291 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7122. Min Act: -0.0000

Data Index: 110663 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7596. Min Act: -0.0000

Data Index: 853761 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7109. Min Act: -0.0000

Data Index: 657395 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.6660. Min Act: -0.0000

Data Index: 413757 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.7062. Min Act: -0.0000

Data Index: 811359 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 1.0669. Min Range: -1.0669

Max Act: 0.6989. Min Act: -0.0000

Data Index: 236198 (C4 (Web Text))

Max Activating Token Index: 36