Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 643 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.9998. Min Act: -0.0000

Data Index: 594285 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.9158. Min Act: -0.0000

Data Index: 46865 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.6621. Min Act: -0.0000

Data Index: 545481 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.7637. Min Act: -0.0000

Data Index: 589603 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.6343. Min Act: -0.0000

Data Index: 1318738 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.7556. Min Act: -0.0000

Data Index: 857822 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.6010. Min Act: -0.0000

Data Index: 1129181 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.3040. Min Act: -0.0000

Data Index: 952469 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.4662. Min Act: -0.0000

Data Index: 372445 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.4443. Min Act: -0.0000

Data Index: 1311948 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.4501. Min Act: -0.0000

Data Index: 493779 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.3050. Min Act: -0.0000

Data Index: 225916 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.4112. Min Act: -0.0000

Data Index: 1155840 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.4102. Min Act: -0.0000

Data Index: 154113 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.2905. Min Act: -0.0000

Data Index: 45374 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.3874. Min Act: -0.0000

Data Index: 617227 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.4060. Min Act: -0.0000

Data Index: 476300 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.3846. Min Act: -0.0000

Data Index: 699298 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.2452. Min Act: -0.0000

Data Index: 680046 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 2.9998. Min Range: -2.9998

Max Act: 2.3747. Min Act: -0.0000

Data Index: 1164637 (C4 (Web Text))

Max Activating Token Index: 945