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

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

Neuron 556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8905. Min Act: -0.0002

Data Index: 939916 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7770. Min Act: -0.0002

Data Index: 1277963 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8194. Min Act: -0.0002

Data Index: 1330205 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8222. Min Act: -0.0002

Data Index: 250222 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.8009. Min Act: -0.0002

Data Index: 137933 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7539. Min Act: -0.0002

Data Index: 1164894 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7661. Min Act: -0.0002

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7411. Min Act: -0.0002

Data Index: 884418 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7395. Min Act: -0.0002

Data Index: 981372 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7471. Min Act: -0.0002

Data Index: 134514 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7389. Min Act: -0.0002

Data Index: 74788 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7583. Min Act: -0.0002

Data Index: 471431 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7509. Min Act: -0.0002

Data Index: 1017598 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7820. Min Act: -0.0002

Data Index: 573802 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7029. Min Act: -0.0002

Data Index: 204045 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.6768. Min Act: -0.0002

Data Index: 792889 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7450. Min Act: -0.0002

Data Index: 583479 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7461. Min Act: -0.0002

Data Index: 603413 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7426. Min Act: -0.0002

Data Index: 886796 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.8905. Min Range: -0.8905

Max Act: 0.7174. Min Act: -0.0002

Data Index: 617717 (C4 (Web Text))

Max Activating Token Index: 745