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

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

Neuron 2587 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: 1.3372. Min Range: -1.3372

Max Act: 1.3128. Min Act: -0.0001

Data Index: 1235416 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.3372. Min Act: -0.0001

Data Index: 1304805 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.1907. Min Act: -0.0001

Data Index: 885001 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.1008. Min Act: -0.0001

Data Index: 1208472 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.1441. Min Act: -0.0001

Data Index: 969626 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.3372. Min Range: -1.3372

Max Act: 0.9866. Min Act: -0.0001

Data Index: 261554 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0668. Min Act: -0.0001

Data Index: 589504 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.1319. Min Act: -0.0001

Data Index: 945414 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.1368. Min Act: -0.0001

Data Index: 909665 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0811. Min Act: -0.0001

Data Index: 171426 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0911. Min Act: -0.0001

Data Index: 251047 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.1162. Min Act: -0.0001

Data Index: 751967 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0704. Min Act: -0.0001

Data Index: 1339877 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0524. Min Act: -0.0001

Data Index: 718348 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.3372. Min Range: -1.3372

Max Act: 0.9749. Min Act: -0.0001

Data Index: 195770 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 1.3372. Min Range: -1.3372

Max Act: 0.9469. Min Act: -0.0001

Data Index: 41525 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0633. Min Act: -0.0001

Data Index: 403306 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.3372. Min Range: -1.3372

Max Act: 1.0050. Min Act: -0.0001

Data Index: 215937 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.3372. Min Range: -1.3372

Max Act: 0.9754. Min Act: -0.0001

Data Index: 648864 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.3372. Min Range: -1.3372

Max Act: 0.9795. Min Act: -0.0001

Data Index: 555848 (C4 (Web Text))

Max Activating Token Index: 683