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

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

Neuron 4694 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.2943. Min Act: 0.0000

Data Index: 219581 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.2173. Min Act: 0.0001

Data Index: 1068662 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.1013. Min Act: -0.0000

Data Index: 913505 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0762. Min Act: -0.0000

Data Index: 677547 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0944. Min Act: -0.0000

Data Index: 395022 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9945. Min Act: 0.0000

Data Index: 1275837 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0308. Min Act: -0.0000

Data Index: 903696 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1007498 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9633. Min Act: 0.0000

Data Index: 452271 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.2943. Min Range: -1.2943

Max Act: 1.0231. Min Act: -0.0000

Data Index: 324893 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1042590 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9470. Min Act: 0.0000

Data Index: 1008159 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9786. Min Act: -0.0000

Data Index: 689001 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8673. Min Act: -0.0000

Data Index: 1245290 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1074539 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.9108. Min Act: -0.0000

Data Index: 648098 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8820. Min Act: -0.0000

Data Index: 150599 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1230924 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.8205. Min Act: -0.0000

Data Index: 742287 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.2943. Min Range: -1.2943

Max Act: 0.7537. Min Act: 0.0000

Data Index: 635039 (C4 (Web Text))

Max Activating Token Index: 390