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

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

Neuron 4143 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: 1.3639. Min Range: -1.3639

Max Act: 1.3022. Min Act: -0.0000

Data Index: 623459 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.3639. Min Range: -1.3639

Max Act: 1.3639. Min Act: -0.0000

Data Index: 232714 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.3639. Min Range: -1.3639

Max Act: 1.1330. Min Act: -0.0000

Data Index: 949405 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 1.3639. Min Range: -1.3639

Max Act: 1.0651. Min Act: -0.0000

Data Index: 332215 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.3639. Min Range: -1.3639

Max Act: 1.0929. Min Act: -0.0000

Data Index: 46853 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.9809. Min Act: -0.0000

Data Index: 1310933 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.9935. Min Act: -0.0000

Data Index: 320168 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 1.3639. Min Range: -1.3639

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1111916 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.3639. Min Range: -1.3639

Max Act: 1.0066. Min Act: -0.0000

Data Index: 798428 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.9453. Min Act: -0.0000

Data Index: 514657 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1018471 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.9568. Min Act: -0.0000

Data Index: 549126 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8776. Min Act: -0.0000

Data Index: 877749 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8643. Min Act: -0.0000

Data Index: 827915 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8831. Min Act: -0.0000

Data Index: 976840 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1256862 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.9066. Min Act: -0.0000

Data Index: 811916 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8125. Min Act: -0.0000

Data Index: 958765 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8059. Min Act: -0.0000

Data Index: 386099 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.3639. Min Range: -1.3639

Max Act: 0.8270. Min Act: -0.0000

Data Index: 481478 (C4 (Web Text))

Max Activating Token Index: 212