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

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

Neuron 1285 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.2632. Min Act: -0.0000

Data Index: 1308433 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.3134. Min Act: -0.0000

Data Index: 7032 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0442. Min Act: -0.0000

Data Index: 583269 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.1459. Min Act: -0.0000

Data Index: 89123 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.1333. Min Act: -0.0000

Data Index: 581226 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0645. Min Act: -0.0000

Data Index: 614375 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0608. Min Act: -0.0000

Data Index: 762167 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.2767. Min Act: -0.0001

Data Index: 1349568 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0267. Min Act: -0.0000

Data Index: 844240 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0011. Min Act: -0.0000

Data Index: 437876 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 2.3134. Min Range: -2.3134

Max Act: 1.9833. Min Act: -0.0000

Data Index: 1119366 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 2.3134. Min Range: -2.3134

Max Act: 1.9938. Min Act: -0.0000

Data Index: 1211193 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.1770. Min Act: -0.0001

Data Index: 921189 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.1905. Min Act: -0.0000

Data Index: 126832 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0535. Min Act: -0.0000

Data Index: 587570 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 2.3134. Min Range: -2.3134

Max Act: 1.9442. Min Act: -0.0000

Data Index: 1286042 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 2.3134. Min Range: -2.3134

Max Act: 2.0419. Min Act: -0.0000

Data Index: 20856 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 2.3134. Min Range: -2.3134

Max Act: 1.9126. Min Act: -0.0000

Data Index: 555967 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 2.3134. Min Range: -2.3134

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1315590 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 2.3134. Min Range: -2.3134

Max Act: 1.7452. Min Act: -0.0000

Data Index: 724242 (C4 (Web Text))

Max Activating Token Index: 749