Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1513231 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1409720 (Python Code)

Max Activating Token Index: 536

Text #2

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1249169 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2109. Min Act: -0.0001

Data Index: 1421003 (Python Code)

Max Activating Token Index: 882

Text #5

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1440060 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2330. Min Act: -0.0001

Data Index: 533687 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1547042 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1403239 (Python Code)

Max Activating Token Index: 934

Text #10

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2095. Min Act: -0.0000

Data Index: 558923 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2030. Min Act: -0.0001

Data Index: 149572 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2072. Min Act: -0.0001

Data Index: 1565112 (Python Code)

Max Activating Token Index: 31

Text #13

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1046612 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1570071 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1650767 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.2226. Min Act: -0.0001

Data Index: 1555687 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.1755. Min Act: -0.0001

Data Index: 1445965 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.1800. Min Act: -0.0001

Data Index: 1538191 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 0.2871. Min Range: -0.2871

Max Act: 0.1910. Min Act: -0.0000

Data Index: 607823 (C4 (Web Text))

Max Activating Token Index: 405