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

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

Neuron 3249 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1062352 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1080. Min Act: -0.0000

Data Index: 591864 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1011. Min Act: -0.0000

Data Index: 122275 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1025. Min Act: -0.0000

Data Index: 538007 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0993. Min Act: -0.0000

Data Index: 543693 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1291994 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1336005 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0959. Min Act: -0.0000

Data Index: 49389 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1286268 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1150940 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0989. Min Act: -0.0000

Data Index: 792539 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0967. Min Act: -0.0000

Data Index: 214249 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1025. Min Act: -0.0000

Data Index: 179165 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0922. Min Act: -0.0000

Data Index: 18451 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0971. Min Act: -0.0000

Data Index: 631183 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0935. Min Act: -0.0000

Data Index: 71174 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0829. Min Act: -0.0000

Data Index: 95686 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0920. Min Act: -0.0001

Data Index: 983003 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0888. Min Act: -0.0000

Data Index: 664469 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0886. Min Act: -0.0000

Data Index: 908988 (C4 (Web Text))

Max Activating Token Index: 307