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

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

Neuron 2643 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1266549 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1417. Min Act: -0.0000

Data Index: 232727 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1250. Min Act: -0.0000

Data Index: 442342 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1535565 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1391. Min Act: -0.0000

Data Index: 456313 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1231468 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1149907 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1070. Min Act: -0.0000

Data Index: 93041 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1061. Min Act: -0.0000

Data Index: 995786 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1183. Min Act: -0.0000

Data Index: 689361 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1134. Min Act: -0.0000

Data Index: 651591 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1049. Min Act: -0.0000

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0946. Min Act: -0.0000

Data Index: 454446 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0947. Min Act: -0.0000

Data Index: 456418 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0887. Min Act: -0.0000

Data Index: 822467 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0842. Min Act: -0.0000

Data Index: 414190 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1054376 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0900. Min Act: -0.0000

Data Index: 286009 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1202608 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1451. Min Range: -0.1451

Max Act: 0.0911. Min Act: -0.0000

Data Index: 536015 (C4 (Web Text))

Max Activating Token Index: 140