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

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

Neuron 3391 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.7554. Min Act: -0.0001

Data Index: 40879 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.6806. Min Act: -0.0001

Data Index: 353614 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.4544. Min Act: -0.0000

Data Index: 398435 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.2441. Min Act: -0.0000

Data Index: 551568 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.1306. Min Act: -0.0000

Data Index: 129842 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.0256. Min Act: -0.0000

Data Index: 933005 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.2120. Min Act: -0.0000

Data Index: 647202 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.7986. Min Act: -0.0000

Data Index: 196225 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1061035 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.8693. Min Act: -0.0000

Data Index: 1327366 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.0745. Min Act: -0.0001

Data Index: 196090 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1293183 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.7272. Min Act: -0.0000

Data Index: 435604 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.9353. Min Act: -0.0000

Data Index: 1186884 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.8098. Min Act: -0.0000

Data Index: 1282479 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.9305. Min Act: -0.0001

Data Index: 608010 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.7554. Min Range: -2.7554

Max Act: 2.0112. Min Act: -0.0000

Data Index: 238571 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.6714. Min Act: -0.0000

Data Index: 1293394 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.7681. Min Act: -0.0001

Data Index: 506485 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 2.7554. Min Range: -2.7554

Max Act: 1.6714. Min Act: -0.0000

Data Index: 344148 (C4 (Web Text))

Max Activating Token Index: 745