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

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

Neuron 3901 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5605. Min Act: -0.0000

Data Index: 844375 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5560. Min Act: -0.0000

Data Index: 983420 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.5035. Min Act: -0.0000

Data Index: 670311 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4614. Min Act: -0.0000

Data Index: 674955 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4682. Min Act: -0.0000

Data Index: 560583 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4662. Min Act: 0.0000

Data Index: 1144040 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4817. Min Act: -0.0000

Data Index: 466047 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4426. Min Act: -0.0000

Data Index: 512270 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4611. Min Act: 0.0000

Data Index: 511622 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4347. Min Act: -0.0000

Data Index: 639622 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4300. Min Act: -0.0000

Data Index: 226368 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4305. Min Act: -0.0000

Data Index: 674393 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1257473 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4208. Min Act: -0.0000

Data Index: 910016 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4332. Min Act: -0.0000

Data Index: 81193 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1191251 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1249821 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4164. Min Act: -0.0000

Data Index: 793860 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4022. Min Act: -0.0000

Data Index: 317561 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.5605. Min Range: -0.5605

Max Act: 0.4149. Min Act: -0.0000

Data Index: 725189 (C4 (Web Text))

Max Activating Token Index: 87