Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 836 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.3680. Min Act: -0.0000

Data Index: 263492 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1207617 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2536. Min Act: -0.0000

Data Index: 385085 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2717. Min Act: -0.0000

Data Index: 620973 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2259. Min Act: -0.0001

Data Index: 62374 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2345. Min Act: -0.0000

Data Index: 900247 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2006. Min Act: -0.0000

Data Index: 962689 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1999. Min Act: -0.0000

Data Index: 337495 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1986. Min Act: -0.0000

Data Index: 186111 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1979. Min Act: -0.0000

Data Index: 527160 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1043095 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2085. Min Act: -0.0000

Data Index: 582883 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2152. Min Act: -0.0000

Data Index: 357455 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2083. Min Act: -0.0000

Data Index: 385023 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2004. Min Act: -0.0000

Data Index: 161533 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.2119. Min Act: -0.0000

Data Index: 336109 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1868. Min Act: -0.0001

Data Index: 1095047 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1916. Min Act: -0.0000

Data Index: 554785 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1840. Min Act: -0.0000

Data Index: 815820 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.3680. Min Range: -0.3680

Max Act: 0.1858. Min Act: -0.0000

Data Index: 145754 (C4 (Web Text))

Max Activating Token Index: 269