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

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

Neuron 3222 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: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0000

Data Index: 59379 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8556. Min Act: -0.0000

Data Index: 372817 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8082. Min Act: -0.0000

Data Index: 353113 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8115. Min Act: -0.0000

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7247. Min Act: -0.0000

Data Index: 783750 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1114134 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1353856 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6131. Min Act: -0.0000

Data Index: 283396 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6536. Min Act: -0.0000

Data Index: 597755 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6383. Min Act: -0.0000

Data Index: 855453 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6180. Min Act: -0.0000

Data Index: 629295 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6396. Min Act: -0.0000

Data Index: 690067 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6245. Min Act: -0.0000

Data Index: 617442 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1063922 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1092621 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5643. Min Act: -0.0000

Data Index: 730066 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1086247 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6003. Min Act: -0.0000

Data Index: 944023 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.5961. Min Act: -0.0000

Data Index: 387438 (C4 (Web Text))

Max Activating Token Index: 272