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

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

Neuron 5554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5910. Min Act: -0.0001

Data Index: 652087 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.6044. Min Act: -0.0000

Data Index: 146536 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5870. Min Act: -0.0000

Data Index: 176775 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5846. Min Act: -0.0000

Data Index: 889132 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5526. Min Act: -0.0000

Data Index: 21427 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5671. Min Act: -0.0000

Data Index: 428351 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5780. Min Act: -0.0001

Data Index: 539154 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5522. Min Act: -0.0000

Data Index: 1307816 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5585. Min Act: -0.0000

Data Index: 480954 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5367. Min Act: -0.0000

Data Index: 262398 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5155. Min Act: -0.0000

Data Index: 602466 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4825. Min Act: -0.0000

Data Index: 14851 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4999. Min Act: -0.0000

Data Index: 100821 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1186871 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4637. Min Act: -0.0000

Data Index: 182461 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1083495 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4760. Min Act: -0.0000

Data Index: 854164 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1269814 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4705. Min Act: -0.0000

Data Index: 937377 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4471. Min Act: -0.0000

Data Index: 859978 (C4 (Web Text))

Max Activating Token Index: 886