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

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

Neuron 2024 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: 1.4643. Min Range: -1.4643

Max Act: 1.4643. Min Act: -0.0000

Data Index: 544441 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.4370. Min Act: -0.0000

Data Index: 542666 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.3892. Min Act: -0.0000

Data Index: 396546 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.3271. Min Act: -0.0000

Data Index: 69812 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.2662. Min Act: -0.0000

Data Index: 1256737 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.2692. Min Act: -0.0000

Data Index: 808680 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.2190. Min Act: -0.0000

Data Index: 89612 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1885. Min Act: 0.0000

Data Index: 523467 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1794. Min Act: -0.0000

Data Index: 60046 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1850. Min Act: -0.0000

Data Index: 127127 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1598. Min Act: -0.0000

Data Index: 127234 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1486. Min Act: 0.0001

Data Index: 744365 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1349. Min Act: -0.0000

Data Index: 923149 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1319. Min Act: -0.0000

Data Index: 107097 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.1276. Min Act: -0.0000

Data Index: 653441 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.0925. Min Act: 0.0000

Data Index: 611499 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.0908. Min Act: -0.0000

Data Index: 587866 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.0209. Min Act: -0.0000

Data Index: 593365 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.0469. Min Act: 0.0000

Data Index: 1211725 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.4643. Min Range: -1.4643

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1202227 (C4 (Web Text))

Max Activating Token Index: 130