Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1317 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.9929. Min Act: -0.0003

Data Index: 1254348 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8899. Min Act: -0.0003

Data Index: 167091 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 1.1484. Min Range: -1.1484

Max Act: 1.1484. Min Act: -0.0003

Data Index: 116780 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.9327. Min Act: -0.0003

Data Index: 671108 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 1.1484. Min Range: -1.1484

Max Act: 1.0352. Min Act: -0.0003

Data Index: 653563 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.1484. Min Range: -1.1484

Max Act: 1.0073. Min Act: -0.0003

Data Index: 823967 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8846. Min Act: -0.0003

Data Index: 1038284 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.1484. Min Range: -1.1484

Max Act: 1.0090. Min Act: -0.0003

Data Index: 389567 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.9999. Min Act: -0.0003

Data Index: 1054283 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8228. Min Act: -0.0003

Data Index: 1088181 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8611. Min Act: -0.0003

Data Index: 483108 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8942. Min Act: -0.0004

Data Index: 2258 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8892. Min Act: -0.0003

Data Index: 1355811 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8790. Min Act: -0.0003

Data Index: 130248 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8553. Min Act: -0.0003

Data Index: 1237440 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.9268. Min Act: -0.0003

Data Index: 1231443 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.9583. Min Act: -0.0003

Data Index: 573385 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8158. Min Act: -0.0003

Data Index: 585908 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.8848. Min Act: -0.0003

Data Index: 637443 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 1.1484. Min Range: -1.1484

Max Act: 0.7807. Min Act: -0.0003

Data Index: 479273 (C4 (Web Text))

Max Activating Token Index: 126