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

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

Neuron 4050 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.6897. Min Act: -0.0000

Data Index: 389200 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4728. Min Act: 0.0001

Data Index: 1050652 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5087. Min Act: -0.0000

Data Index: 60535 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4899. Min Act: -0.0000

Data Index: 398674 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5056. Min Act: 0.0001

Data Index: 698534 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4874. Min Act: 0.0000

Data Index: 908466 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.5061. Min Act: -0.0000

Data Index: 20347 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4842. Min Act: -0.0000

Data Index: 549879 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4848. Min Act: -0.0000

Data Index: 913656 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1064059 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4585. Min Act: -0.0000

Data Index: 462297 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4410. Min Act: -0.0000

Data Index: 42216 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4641. Min Act: 0.0000

Data Index: 1126348 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1103874 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4589. Min Act: -0.0000

Data Index: 114636 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4508. Min Act: -0.0000

Data Index: 29048 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4448. Min Act: -0.0000

Data Index: 124797 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4614. Min Act: -0.0000

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1050087 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.6897. Min Range: -0.6897

Max Act: 0.4486. Min Act: -0.0000

Data Index: 963198 (C4 (Web Text))

Max Activating Token Index: 359