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

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

Neuron 3845 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.3205. Min Act: -0.0001

Data Index: 938404 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.3340. Min Act: -0.0001

Data Index: 633966 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.2630. Min Act: -0.0001

Data Index: 1256513 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1719. Min Act: -0.0001

Data Index: 7264 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.2301. Min Act: -0.0001

Data Index: 1294791 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1788. Min Act: -0.0001

Data Index: 1274381 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.2458. Min Act: -0.0001

Data Index: 131382 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1346. Min Act: -0.0001

Data Index: 858452 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.2106. Min Act: -0.0001

Data Index: 430384 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1799. Min Act: -0.0001

Data Index: 296688 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1206. Min Act: -0.0001

Data Index: 1204306 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1611. Min Act: -0.0001

Data Index: 1011793 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1405. Min Act: -0.0001

Data Index: 484612 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1191. Min Act: -0.0001

Data Index: 948918 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.2218. Min Act: -0.0001

Data Index: 1320774 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1406. Min Act: -0.0001

Data Index: 377239 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1326. Min Act: -0.0001

Data Index: 625037 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1121. Min Act: -0.0001

Data Index: 1122708 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1105. Min Act: -0.0001

Data Index: 1088038 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.3340. Min Range: -1.3340

Max Act: 1.1151. Min Act: -0.0001

Data Index: 501663 (C4 (Web Text))

Max Activating Token Index: 807