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

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

Neuron 3388 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.1033. Min Act: -0.0001

Data Index: 1258459 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.0920. Min Act: -0.0000

Data Index: 925897 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.1007. Min Act: -0.0001

Data Index: 1177380 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.0088. Min Act: -0.0001

Data Index: 1168691 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.0418. Min Act: -0.0001

Data Index: 1147685 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9662. Min Act: -0.0000

Data Index: 542761 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.0242. Min Act: -0.0000

Data Index: 80280 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9844. Min Act: -0.0000

Data Index: 13804 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.0262. Min Act: -0.0000

Data Index: 713370 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9812. Min Act: -0.0001

Data Index: 1291842 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.1033. Min Range: -1.1033

Max Act: 1.0095. Min Act: -0.0000

Data Index: 934977 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9821. Min Act: -0.0000

Data Index: 657961 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1355781 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9091. Min Act: -0.0000

Data Index: 123627 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9051. Min Act: -0.0001

Data Index: 1136295 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9670. Min Act: -0.0000

Data Index: 551475 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9343. Min Act: -0.0001

Data Index: 661769 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9333. Min Act: -0.0001

Data Index: 318588 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.9283. Min Act: -0.0001

Data Index: 682511 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 1.1033. Min Range: -1.1033

Max Act: 0.8634. Min Act: -0.0001

Data Index: 15210 (C4 (Web Text))

Max Activating Token Index: 363