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

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

Neuron 1056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.5644. Min Act: -0.0001

Data Index: 939272 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.5654. Min Act: -0.0001

Data Index: 615677 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.3975. Min Act: -0.0001

Data Index: 502995 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4703. Min Act: -0.0001

Data Index: 770948 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1317775 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4229. Min Act: -0.0001

Data Index: 741077 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.5089. Min Act: -0.0001

Data Index: 211962 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4462. Min Act: -0.0001

Data Index: 471297 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1089455 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4559. Min Act: -0.0001

Data Index: 113522 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4242. Min Act: -0.0001

Data Index: 361345 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4957. Min Act: -0.0001

Data Index: 1074493 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4653. Min Act: -0.0001

Data Index: 26927 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4958. Min Act: -0.0001

Data Index: 1358726 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4509. Min Act: -0.0001

Data Index: 265429 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.2195. Min Act: -0.0001

Data Index: 453779 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1023002 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.4049. Min Act: -0.0001

Data Index: 638952 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.3546. Min Act: -0.0001

Data Index: 1328506 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.6227. Min Range: -0.6227

Max Act: 0.3895. Min Act: -0.0001

Data Index: 334396 (C4 (Web Text))

Max Activating Token Index: 281