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

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

Neuron 1460 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: 0.6934. Min Range: -0.6934

Max Act: 0.6934. Min Act: -0.0000

Data Index: 49329 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6227. Min Act: -0.0000

Data Index: 701735 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.6151. Min Act: -0.0000

Data Index: 546735 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5203. Min Act: -0.0000

Data Index: 82154 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1157145 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1175550 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.5066. Min Act: -0.0000

Data Index: 557476 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4712. Min Act: -0.0000

Data Index: 956491 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4999. Min Act: -0.0000

Data Index: 617117 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4588. Min Act: -0.0000

Data Index: 840481 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4480. Min Act: -0.0000

Data Index: 467754 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4333. Min Act: -0.0000

Data Index: 713837 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4443. Min Act: -0.0000

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4683. Min Act: -0.0000

Data Index: 611366 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4473. Min Act: -0.0000

Data Index: 378341 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4571. Min Act: -0.0000

Data Index: 116259 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4367. Min Act: -0.0000

Data Index: 594409 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4760. Min Act: -0.0000

Data Index: 900114 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4615. Min Act: -0.0000

Data Index: 848138 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.6934. Min Range: -0.6934

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1242979 (C4 (Web Text))

Max Activating Token Index: 985