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

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

Neuron 4898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0000

Data Index: 14185 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6620. Min Act: 0.0000

Data Index: 116617 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5485. Min Act: -0.0000

Data Index: 527629 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5540. Min Act: -0.0000

Data Index: 376872 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1263860 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1034721 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4721. Min Act: -0.0000

Data Index: 382188 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4791. Min Act: -0.0000

Data Index: 956555 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4775. Min Act: -0.0000

Data Index: 550369 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1084020 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4814. Min Act: -0.0000

Data Index: 119367 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4483. Min Act: -0.0000

Data Index: 106353 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4448. Min Act: -0.0000

Data Index: 854305 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4205. Min Act: -0.0000

Data Index: 546176 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4680. Min Act: -0.0000

Data Index: 264992 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4519. Min Act: -0.0000

Data Index: 335335 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4830. Min Act: -0.0000

Data Index: 36961 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1202289 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4333. Min Act: -0.0000

Data Index: 384376 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.4628. Min Act: -0.0000

Data Index: 143506 (C4 (Web Text))

Max Activating Token Index: 29