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

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

Neuron 3774 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: 5.0454. Min Range: -5.0454

Max Act: 4.8524. Min Act: -0.0001

Data Index: 1138982 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 5.0454. Min Range: -5.0454

Max Act: 5.0454. Min Act: -0.0001

Data Index: 386995 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6421. Min Act: -0.0001

Data Index: 361462 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.8356. Min Act: -0.0001

Data Index: 1038130 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.6227. Min Act: -0.0001

Data Index: 601319 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.3719. Min Act: -0.0001

Data Index: 979010 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.5390. Min Act: -0.0001

Data Index: 1181310 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 5.0454. Min Range: -5.0454

Max Act: 4.7001. Min Act: -0.0001

Data Index: 333452 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 5.0454. Min Range: -5.0454

Max Act: 3.9884. Min Act: -0.0001

Data Index: 583343 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 5.0454. Min Range: -5.0454

Max Act: 2.0838. Min Act: -0.0001

Data Index: 143149 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.9137. Min Act: -0.0001

Data Index: 104763 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.9003. Min Act: -0.0001

Data Index: 1203568 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.8881. Min Act: -0.0001

Data Index: 1217469 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.8539. Min Act: -0.0001

Data Index: 778814 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.8694. Min Act: -0.0001

Data Index: 600593 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.8886. Min Act: -0.0001

Data Index: 899711 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.7475. Min Act: -0.0001

Data Index: 1352832 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.8318. Min Act: -0.0001

Data Index: 421065 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.7113. Min Act: -0.0001

Data Index: 1116061 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 5.0454. Min Range: -5.0454

Max Act: 1.7614. Min Act: -0.0001

Data Index: 34839 (C4 (Web Text))

Max Activating Token Index: 250