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

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

Neuron 5247 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4483. Min Act: -0.0001

Data Index: 701124 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4045. Min Act: -0.0001

Data Index: 422284 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.4339. Min Act: -0.0001

Data Index: 734876 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3962. Min Act: -0.0001

Data Index: 400486 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3512. Min Act: -0.0001

Data Index: 882104 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3691. Min Act: -0.0001

Data Index: 883412 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1352838 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3266. Min Act: -0.0001

Data Index: 928312 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3638. Min Act: -0.0001

Data Index: 513217 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3329. Min Act: -0.0001

Data Index: 742827 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3038. Min Act: -0.0001

Data Index: 346151 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1029851 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2609. Min Act: -0.0001

Data Index: 176634 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3157. Min Act: -0.0001

Data Index: 434568 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2294. Min Act: -0.0001

Data Index: 477082 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2908. Min Act: -0.0000

Data Index: 364385 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2589. Min Act: -0.0001

Data Index: 531645 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2441. Min Act: -0.0001

Data Index: 49939 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.3199. Min Act: -0.0001

Data Index: 236300 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.4483. Min Range: -0.4483

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1380017 (Python Code)

Max Activating Token Index: 849