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

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

Neuron 1392 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: 0.9327. Min Range: -0.9327

Max Act: 0.9327. Min Act: -0.0000

Data Index: 411161 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.8882. Min Act: -0.0000

Data Index: 459384 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1170273 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7868. Min Act: -0.0000

Data Index: 641515 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7630. Min Act: -0.0000

Data Index: 1073175 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7329. Min Act: -0.0000

Data Index: 762909 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7516. Min Act: -0.0000

Data Index: 157681 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6967. Min Act: -0.0000

Data Index: 861040 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7384. Min Act: 0.0000

Data Index: 970768 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7096. Min Act: -0.0000

Data Index: 347321 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1164 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6700. Min Act: 0.0000

Data Index: 557472 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6434. Min Act: -0.0000

Data Index: 303148 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6634. Min Act: -0.0000

Data Index: 273212 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6410. Min Act: -0.0000

Data Index: 209105 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6396. Min Act: -0.0000

Data Index: 289076 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1200831 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.5672. Min Act: -0.0000

Data Index: 394271 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1177947 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.9327. Min Range: -0.9327

Max Act: 0.6202. Min Act: -0.0000

Data Index: 39315 (C4 (Web Text))

Max Activating Token Index: 540