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

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

Neuron 405 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: 1.6644. Min Range: -1.6644

Max Act: 1.6166. Min Act: -0.0000

Data Index: 767613 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1241022 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.3540. Min Act: 0.0000

Data Index: 843215 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.3862. Min Act: -0.0000

Data Index: 4551 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.2192. Min Act: -0.0001

Data Index: 426720 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.2524. Min Act: -0.0001

Data Index: 59676 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1407. Min Act: -0.0000

Data Index: 321334 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0986. Min Act: -0.0000

Data Index: 991476 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1566. Min Act: -0.0000

Data Index: 397909 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1692. Min Act: -0.0001

Data Index: 62952 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1627. Min Act: -0.0000

Data Index: 1241672 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1518. Min Act: -0.0000

Data Index: 687831 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1763. Min Act: -0.0000

Data Index: 666052 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0630. Min Act: -0.0000

Data Index: 454514 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0739. Min Act: -0.0000

Data Index: 438908 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0947. Min Act: -0.0001

Data Index: 555144 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0904. Min Act: -0.0000

Data Index: 301255 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0180. Min Act: -0.0001

Data Index: 1034705 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.0756. Min Act: -0.0001

Data Index: 793181 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.6644. Min Range: -1.6644

Max Act: 1.1060. Min Act: -0.0001

Data Index: 557204 (C4 (Web Text))

Max Activating Token Index: 934