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

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

Neuron 2621 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: 0.1784. Min Range: -0.1784

Max Act: 0.1784. Min Act: -0.0000

Data Index: 613326 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1651. Min Act: -0.0000

Data Index: 656903 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1302409 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1455. Min Act: -0.0000

Data Index: 347672 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1587. Min Act: -0.0000

Data Index: 282010 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1299163 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1421. Min Act: -0.0000

Data Index: 311388 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1362. Min Act: -0.0000

Data Index: 718310 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1270. Min Act: -0.0000

Data Index: 424875 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1527. Min Act: -0.0000

Data Index: 1092019 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1344. Min Act: -0.0000

Data Index: 800017 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1466. Min Act: -0.0000

Data Index: 744979 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1017844 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1391. Min Act: -0.0000

Data Index: 97236 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1220. Min Act: -0.0000

Data Index: 467147 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1337. Min Act: -0.0000

Data Index: 754358 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1336. Min Act: -0.0000

Data Index: 893266 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1030968 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1182. Min Act: -0.0000

Data Index: 38543 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.1784. Min Range: -0.1784

Max Act: 0.1220. Min Act: -0.0000

Data Index: 56913 (C4 (Web Text))

Max Activating Token Index: 438