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

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

Neuron 4978 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0204. Min Range: -2.0204

Max Act: 2.0204. Min Act: -0.0000

Data Index: 132617 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1525786 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.9044. Min Act: -0.0000

Data Index: 1632189 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.6940. Min Act: -0.0000

Data Index: 917805 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.7324. Min Act: -0.0000

Data Index: 783407 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.7170. Min Act: -0.0000

Data Index: 66491 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.6991. Min Act: -0.0000

Data Index: 1194328 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.7740. Min Act: -0.0000

Data Index: 1037024 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1388256 (Python Code)

Max Activating Token Index: 793

Text #9

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.6167. Min Act: -0.0000

Data Index: 1612378 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1594478 (Python Code)

Max Activating Token Index: 834

Text #11

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.6896. Min Act: -0.0000

Data Index: 904432 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.4737. Min Act: -0.0000

Data Index: 1508162 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.4667. Min Act: -0.0000

Data Index: 777391 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1396109 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.5199. Min Act: -0.0000

Data Index: 77769 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1412776 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1108248 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.5666. Min Act: -0.0000

Data Index: 1276373 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 2.0204. Min Range: -2.0204

Max Act: 1.4863. Min Act: -0.0000

Data Index: 313429 (C4 (Web Text))

Max Activating Token Index: 516