Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1239 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5538. Min Act: -0.0001

Data Index: 1154095 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5353. Min Act: -0.0001

Data Index: 743304 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5022. Min Act: -0.0001

Data Index: 704868 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4817. Min Act: -0.0000

Data Index: 533712 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5104. Min Act: -0.0001

Data Index: 1357275 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4845. Min Act: -0.0001

Data Index: 114027 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1042664 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4434. Min Act: -0.0000

Data Index: 699199 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4675. Min Act: -0.0001

Data Index: 903935 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4671. Min Act: -0.0001

Data Index: 878105 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4887. Min Act: -0.0000

Data Index: 507598 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4314. Min Act: -0.0001

Data Index: 872761 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4280. Min Act: -0.0001

Data Index: 37422 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.5010. Min Act: -0.0001

Data Index: 245319 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4724. Min Act: -0.0001

Data Index: 1285490 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1349847 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4365. Min Act: -0.0001

Data Index: 1107252 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4355. Min Act: -0.0001

Data Index: 379332 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4422. Min Act: -0.0001

Data Index: 514411 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 0.5538. Min Range: -0.5538

Max Act: 0.4345. Min Act: -0.0001

Data Index: 389869 (C4 (Web Text))

Max Activating Token Index: 243