Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1663. Min Range: -3.1663

Max Act: 3.1663. Min Act: -0.0000

Data Index: 885261 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.9902. Min Act: -0.0000

Data Index: 541450 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.7988. Min Act: -0.0000

Data Index: 360608 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.7906. Min Act: -0.0000

Data Index: 531482 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.6908. Min Act: -0.0000

Data Index: 696644 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.6385. Min Act: -0.0000

Data Index: 1140601 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.4985. Min Act: -0.0000

Data Index: 315171 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.7656. Min Act: -0.0000

Data Index: 1086178 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.5267. Min Act: -0.0000

Data Index: 506968 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.6646. Min Act: -0.0000

Data Index: 574667 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.5181. Min Act: -0.0000

Data Index: 1332182 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.3639. Min Act: -0.0000

Data Index: 389840 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.3755. Min Act: -0.0000

Data Index: 625414 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.4822. Min Act: -0.0000

Data Index: 591738 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.4742. Min Act: -0.0000

Data Index: 111358 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.4393. Min Act: -0.0000

Data Index: 838346 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.5401. Min Act: -0.0000

Data Index: 558028 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.4074. Min Act: -0.0000

Data Index: 1338113 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.2383. Min Act: -0.0000

Data Index: 644649 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 3.1663. Min Range: -3.1663

Max Act: 2.2338. Min Act: -0.0000

Data Index: 1108647 (C4 (Web Text))

Max Activating Token Index: 811