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

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

Neuron 1492 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.4160. Min Act: -0.0001

Data Index: 1206026 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.3601. Min Act: -0.0001

Data Index: 416327 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.3023. Min Act: -0.0000

Data Index: 59617 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.1276. Min Act: -0.0000

Data Index: 942053 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.0601. Min Act: -0.0001

Data Index: 868038 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.1057. Min Act: -0.0001

Data Index: 1357159 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.1064. Min Act: -0.0001

Data Index: 134180 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9743. Min Act: -0.0000

Data Index: 650518 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9756. Min Act: -0.0000

Data Index: 477714 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 1.4160. Min Range: -1.4160

Max Act: 1.0580. Min Act: -0.0001

Data Index: 1057338 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9731. Min Act: -0.0001

Data Index: 387826 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9322. Min Act: -0.0000

Data Index: 882837 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9871. Min Act: -0.0000

Data Index: 777411 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1356084 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9632. Min Act: -0.0001

Data Index: 1247810 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9361. Min Act: -0.0001

Data Index: 124232 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9177. Min Act: -0.0001

Data Index: 184816 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.8431. Min Act: -0.0001

Data Index: 1518964 (Python Code)

Max Activating Token Index: 79

Text #18

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.9041. Min Act: -0.0001

Data Index: 709575 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 1.4160. Min Range: -1.4160

Max Act: 0.7966. Min Act: -0.0000

Data Index: 104017 (C4 (Web Text))

Max Activating Token Index: 1013