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

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

Neuron 3479 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: 2.1966. Min Range: -2.1966

Max Act: 2.1966. Min Act: -0.0000

Data Index: 935377 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.6797. Min Act: -0.0000

Data Index: 1257887 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.6770. Min Act: 0.0000

Data Index: 850724 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.5672. Min Act: -0.0000

Data Index: 54965 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.5520. Min Act: -0.0000

Data Index: 1190351 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.5364. Min Act: -0.0000

Data Index: 638966 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.4942. Min Act: 0.0000

Data Index: 504269 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.3176. Min Act: 0.0002

Data Index: 567389 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.3153. Min Act: 0.0000

Data Index: 781835 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.4008. Min Act: -0.0000

Data Index: 933408 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.3151. Min Act: 0.0001

Data Index: 291002 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2919. Min Act: 0.0001

Data Index: 356072 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2924. Min Act: 0.0000

Data Index: 67631 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2696. Min Act: 0.0002

Data Index: 1123108 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2643. Min Act: 0.0000

Data Index: 329739 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2978. Min Act: 0.0000

Data Index: 1098915 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2575. Min Act: 0.0002

Data Index: 784843 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2098. Min Act: 0.0000

Data Index: 1098504 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2751. Min Act: 0.0001

Data Index: 178106 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 2.1966. Min Range: -2.1966

Max Act: 1.2306. Min Act: -0.0000

Data Index: 664890 (C4 (Web Text))

Max Activating Token Index: 496