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

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

Neuron 2695 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1831. Min Act: -0.0000

Data Index: 572447 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1666. Min Act: -0.0000

Data Index: 538447 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1612. Min Act: -0.0000

Data Index: 416184 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1464. Min Act: -0.0000

Data Index: 653578 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1455177 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1524160 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1333. Min Act: -0.0000

Data Index: 569658 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1360. Min Act: -0.0000

Data Index: 131557 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1182. Min Act: -0.0000

Data Index: 410424 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1345. Min Act: 0.0000

Data Index: 1376230 (Python Code)

Max Activating Token Index: 350

Text #10

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1046225 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1217. Min Act: -0.0000

Data Index: 841848 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1362. Min Act: -0.0000

Data Index: 384509 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1316. Min Act: -0.0000

Data Index: 6866 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1254. Min Act: -0.0000

Data Index: 83214 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1241. Min Act: -0.0000

Data Index: 62256 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1461548 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1374454 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1222. Min Act: -0.0000

Data Index: 238311 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.1831. Min Range: -0.1831

Max Act: 0.1249. Min Act: 0.0000

Data Index: 150664 (C4 (Web Text))

Max Activating Token Index: 45