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

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

Neuron 3210 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: 2.0692. Min Range: -2.0692

Max Act: 2.0692. Min Act: -0.0000

Data Index: 988931 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.5508. Min Act: -0.0000

Data Index: 1065443 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1158118 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.5211. Min Act: -0.0000

Data Index: 450195 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.5280. Min Act: -0.0000

Data Index: 3617 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.5276. Min Act: -0.0000

Data Index: 121197 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3761. Min Act: -0.0000

Data Index: 993102 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1019113 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3875. Min Act: -0.0000

Data Index: 460966 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.4699. Min Act: -0.0000

Data Index: 290046 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3630. Min Act: -0.0000

Data Index: 965403 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3613. Min Act: -0.0000

Data Index: 525435 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3496. Min Act: -0.0000

Data Index: 637397 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3369. Min Act: -0.0000

Data Index: 88502 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3394. Min Act: -0.0000

Data Index: 462181 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3310. Min Act: -0.0000

Data Index: 315297 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3168. Min Act: -0.0000

Data Index: 785449 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1062690 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.3068. Min Act: -0.0000

Data Index: 942042 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 2.0692. Min Range: -2.0692

Max Act: 1.2155. Min Act: -0.0000

Data Index: 638545 (C4 (Web Text))

Max Activating Token Index: 789