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

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

Neuron 932 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7671. Min Act: -0.0000

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.7991. Min Act: -0.0000

Data Index: 198022 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.5902. Min Act: -0.0001

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6919. Min Act: -0.0000

Data Index: 254489 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.3841. Min Act: -0.0000

Data Index: 481883 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.3589. Min Act: -0.0001

Data Index: 47431 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6486. Min Act: -0.0000

Data Index: 1281511 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.3131. Min Act: -0.0000

Data Index: 1045198 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.3237. Min Act: -0.0001

Data Index: 407145 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.2719. Min Act: -0.0000

Data Index: 617491 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.0507. Min Act: -0.0000

Data Index: 272547 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.0289. Min Act: -0.0000

Data Index: 1033858 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.3078. Min Act: -0.0000

Data Index: 1272125 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.6177. Min Act: -0.0000

Data Index: 742940 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.1530. Min Act: -0.0000

Data Index: 1273744 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.3101. Min Act: -0.0000

Data Index: 438286 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.4587. Min Act: -0.0000

Data Index: 426654 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.1636. Min Act: -0.0000

Data Index: 506648 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.1814. Min Act: -0.0000

Data Index: 212722 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.7991. Min Range: -3.7991

Max Act: 3.2936. Min Act: -0.0000

Data Index: 366425 (C4 (Web Text))

Max Activating Token Index: 564