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

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

Neuron 1646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.6910. Min Act: -0.0000

Data Index: 268430 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5874. Min Act: -0.0000

Data Index: 683660 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5217. Min Act: -0.0000

Data Index: 240009 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1012553 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4907. Min Act: -0.0000

Data Index: 920105 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1059566 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4570. Min Act: -0.0000

Data Index: 934484 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1332130 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1083113 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4391. Min Act: -0.0000

Data Index: 998775 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1110429 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1128521 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4168. Min Act: -0.0000

Data Index: 1354815 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4120. Min Act: -0.0000

Data Index: 243336 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4214. Min Act: -0.0000

Data Index: 862486 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4094. Min Act: -0.0000

Data Index: 392399 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1086979 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.4146. Min Act: -0.0000

Data Index: 334384 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1144014 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.6910. Min Range: -0.6910

Max Act: 0.3781. Min Act: -0.0000

Data Index: 1354198 (C4 (Web Text))

Max Activating Token Index: 669