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

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

Neuron 3961 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.6840. Min Act: -0.0003

Data Index: 562352 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.3431. Min Act: -0.0003

Data Index: 257978 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4120. Min Act: -0.0003

Data Index: 466689 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4585. Min Act: -0.0003

Data Index: 1298627 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2798. Min Act: -0.0003

Data Index: 1259547 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2719. Min Act: -0.0003

Data Index: 1126927 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0928. Min Act: -0.0003

Data Index: 1296719 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0986. Min Act: -0.0003

Data Index: 723504 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0624. Min Act: -0.0003

Data Index: 183389 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.2252. Min Act: -0.0003

Data Index: 781594 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.1765. Min Act: -0.0003

Data Index: 832952 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.1344. Min Act: -0.0003

Data Index: 24295 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0218. Min Act: -0.0003

Data Index: 695482 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.6840. Min Range: -1.6840

Max Act: 0.9427. Min Act: -0.0003

Data Index: 899451 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.4091. Min Act: -0.0003

Data Index: 1211608 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 1.6840. Min Range: -1.6840

Max Act: 0.9652. Min Act: -0.0003

Data Index: 66054 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0801. Min Act: -0.0003

Data Index: 1285667 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0452. Min Act: -0.0003

Data Index: 706442 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.1865. Min Act: -0.0003

Data Index: 365986 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.6840. Min Range: -1.6840

Max Act: 1.0123. Min Act: -0.0003

Data Index: 478566 (C4 (Web Text))

Max Activating Token Index: 290