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

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

Neuron 3172 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.8862. Min Act: -0.0000

Data Index: 562212 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.6782. Min Act: -0.0000

Data Index: 785085 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.6940. Min Act: -0.0000

Data Index: 1296921 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.5148. Min Act: -0.0000

Data Index: 605159 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.1915. Min Act: -0.0000

Data Index: 147293 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1006492 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.0332. Min Act: -0.0000

Data Index: 851354 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.9222. Min Act: -0.0000

Data Index: 122040 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.1511. Min Act: -0.0000

Data Index: 428779 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.1133. Min Act: -0.0000

Data Index: 496568 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.0230. Min Act: -0.0000

Data Index: 1796 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.8862. Min Range: -2.8862

Max Act: 2.2230. Min Act: -0.0000

Data Index: 782574 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.9008. Min Act: -0.0000

Data Index: 910803 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.7792. Min Act: -0.0000

Data Index: 684026 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.7980. Min Act: -0.0000

Data Index: 226799 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.7711. Min Act: -0.0000

Data Index: 212479 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.6728. Min Act: -0.0000

Data Index: 1199720 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.7443. Min Act: -0.0000

Data Index: 411921 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.8404. Min Act: -0.0000

Data Index: 1221040 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 2.8862. Min Range: -2.8862

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1220557 (C4 (Web Text))

Max Activating Token Index: 139