Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 86 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.4503. Min Act: -0.0000

Data Index: 433470 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3117. Min Act: -0.0000

Data Index: 895737 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1269744 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2764. Min Act: -0.0000

Data Index: 889112 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2638. Min Act: -0.0000

Data Index: 1365072 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1145964 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2890. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2590. Min Act: -0.0000

Data Index: 75235 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2759. Min Act: -0.0000

Data Index: 642883 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2528. Min Act: -0.0000

Data Index: 728410 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2478. Min Act: -0.0000

Data Index: 711744 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1092181 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1642341 (Python Code)

Max Activating Token Index: 930

Text #13

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1150317 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1415996 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2051. Min Act: -0.0000

Data Index: 130791 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1412584 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2092. Min Act: -0.0000

Data Index: 804642 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1644165 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.2068. Min Act: -0.0000

Data Index: 386091 (C4 (Web Text))

Max Activating Token Index: 520