Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1888 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6936. Min Act: -0.0001

Data Index: 1034227 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7542. Min Act: -0.0001

Data Index: 21118 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7145. Min Act: -0.0001

Data Index: 11274 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6670. Min Act: -0.0001

Data Index: 655631 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7242. Min Act: -0.0001

Data Index: 1312413 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.7032. Min Act: -0.0002

Data Index: 574142 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6226. Min Act: -0.0002

Data Index: 1159003 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6374. Min Act: -0.0001

Data Index: 148246 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6377. Min Act: -0.0001

Data Index: 854086 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6314. Min Act: -0.0002

Data Index: 849276 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5911. Min Act: -0.0002

Data Index: 694113 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6143. Min Act: -0.0001

Data Index: 1215128 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6087. Min Act: -0.0001

Data Index: 278693 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1371795 (Python Code)

Max Activating Token Index: 1008

Text #14

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6306. Min Act: -0.0002

Data Index: 1309824 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6149. Min Act: -0.0001

Data Index: 610007 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1489138 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.6134. Min Act: -0.0002

Data Index: 1081312 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5546. Min Act: -0.0002

Data Index: 840008 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.7542. Min Range: -0.7542

Max Act: 0.5597. Min Act: -0.0002

Data Index: 470246 (C4 (Web Text))

Max Activating Token Index: 241