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

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

Neuron 484 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: 0.3990. Min Range: -0.3990

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1132394 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3990. Min Act: -0.0001

Data Index: 1655628 (Python Code)

Max Activating Token Index: 389

Text #2

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3703. Min Act: -0.0000

Data Index: 503226 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3570. Min Act: -0.0001

Data Index: 1435195 (Python Code)

Max Activating Token Index: 695

Text #4

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1135009 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1445886 (Python Code)

Max Activating Token Index: 926

Text #6

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3105. Min Act: -0.0001

Data Index: 1470866 (Python Code)

Max Activating Token Index: 944

Text #7

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3032. Min Act: -0.0000

Data Index: 36877 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2991. Min Act: -0.0001

Data Index: 1644937 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3223. Min Act: -0.0001

Data Index: 1592697 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2984. Min Act: -0.0001

Data Index: 1593533 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1614355 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2959. Min Act: -0.0001

Data Index: 1473308 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1482029 (Python Code)

Max Activating Token Index: 116

Text #14

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1644470 (Python Code)

Max Activating Token Index: 479

Text #15

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2997. Min Act: -0.0001

Data Index: 1613501 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2974. Min Act: -0.0001

Data Index: 1431842 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2972. Min Act: -0.0000

Data Index: 913278 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.2864. Min Act: -0.0000

Data Index: 595065 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.3990. Min Range: -0.3990

Max Act: 0.3174. Min Act: -0.0001

Data Index: 1517122 (Python Code)

Max Activating Token Index: 940