Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4601 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1620681 (Python Code)

Max Activating Token Index: 369

Text #1

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1457972 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1541. Min Act: -0.0000

Data Index: 374370 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1420. Min Act: -0.0000

Data Index: 1508319 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1486887 (Python Code)

Max Activating Token Index: 892

Text #5

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1341394 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1615988 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1208. Min Act: -0.0000

Data Index: 1470546 (Python Code)

Max Activating Token Index: 235

Text #8

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1329. Min Act: -0.0000

Data Index: 495155 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1175. Min Act: -0.0000

Data Index: 824284 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1215. Min Act: -0.0000

Data Index: 295909 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1656623 (Python Code)

Max Activating Token Index: 580

Text #12

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1566486 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1212. Min Act: -0.0000

Data Index: 600945 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1254. Min Act: -0.0000

Data Index: 1601707 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1636684 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1030. Min Act: -0.0000

Data Index: 829644 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1152. Min Act: -0.0000

Data Index: 831392 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1018. Min Act: -0.0000

Data Index: 794249 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1541. Min Range: -0.1541

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1460118 (Python Code)

Max Activating Token Index: 4