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

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

Neuron 5047 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: 3.2981. Min Range: -3.2981

Max Act: 3.1810. Min Act: -0.0000

Data Index: 498601 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 3.2981. Min Range: -3.2981

Max Act: 3.2981. Min Act: -0.0000

Data Index: 48506 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.2981. Min Range: -3.2981

Max Act: 3.2116. Min Act: -0.0000

Data Index: 153204 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.2981. Min Range: -3.2981

Max Act: 3.1638. Min Act: -0.0000

Data Index: 1006352 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 3.2981. Min Range: -3.2981

Max Act: 3.1033. Min Act: -0.0000

Data Index: 1248028 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.8289. Min Act: -0.0000

Data Index: 946960 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.8636. Min Act: -0.0000

Data Index: 45250 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6961. Min Act: -0.0000

Data Index: 814889 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.9468. Min Act: -0.0000

Data Index: 284221 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6569. Min Act: -0.0000

Data Index: 525040 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6304. Min Act: -0.0000

Data Index: 403789 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6228. Min Act: -0.0000

Data Index: 673677 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.5581. Min Act: -0.0000

Data Index: 311064 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6969. Min Act: -0.0000

Data Index: 61947 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6725. Min Act: -0.0000

Data Index: 439665 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.5059. Min Act: -0.0000

Data Index: 372111 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6313. Min Act: -0.0000

Data Index: 1285618 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.6203. Min Act: -0.0000

Data Index: 463 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.4874. Min Act: -0.0000

Data Index: 21076 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.2981. Min Range: -3.2981

Max Act: 2.7166. Min Act: -0.0000

Data Index: 612452 (C4 (Web Text))

Max Activating Token Index: 179