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

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

Neuron 520 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0002

Data Index: 830052 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1087. Min Act: -0.0002

Data Index: 64574 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1083. Min Act: -0.0002

Data Index: 765285 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1468548 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1087. Min Act: -0.0002

Data Index: 941445 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1029195 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0988. Min Act: -0.0002

Data Index: 244501 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1143554 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0998. Min Act: -0.0002

Data Index: 575281 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0960. Min Act: -0.0002

Data Index: 792860 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0952. Min Act: -0.0002

Data Index: 456804 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0981. Min Act: -0.0002

Data Index: 1046664 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0929. Min Act: -0.0002

Data Index: 324083 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0923. Min Act: -0.0002

Data Index: 662105 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1190975 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1064123 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0922. Min Act: -0.0002

Data Index: 39930 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0920. Min Act: -0.0002

Data Index: 493873 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1603739 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1293235 (C4 (Web Text))

Max Activating Token Index: 813