Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2870 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.4971. Min Act: -0.0000

Data Index: 657235 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.4597. Min Act: -0.0000

Data Index: 714941 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.4778. Min Act: -0.0000

Data Index: 23711 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3904. Min Act: -0.0000

Data Index: 313300 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.4244. Min Act: -0.0000

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.2982. Min Act: -0.0000

Data Index: 950441 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1052674 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3539. Min Act: -0.0000

Data Index: 153842 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3411. Min Act: -0.0000

Data Index: 173797 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3348. Min Act: -0.0000

Data Index: 66822 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3142. Min Act: -0.0000

Data Index: 84825 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3191. Min Act: -0.0000

Data Index: 930189 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.2704. Min Act: -0.0000

Data Index: 286775 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.3368. Min Act: -0.0000

Data Index: 575078 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.4156. Min Act: -0.0000

Data Index: 1059948 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.2903. Min Act: 0.0001

Data Index: 1007362 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.2670. Min Act: -0.0000

Data Index: 493604 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.2298. Min Act: -0.0000

Data Index: 602169 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.1741. Min Act: -0.0000

Data Index: 585710 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 1.4971. Min Range: -1.4971

Max Act: 1.2826. Min Act: -0.0000

Data Index: 218423 (C4 (Web Text))

Max Activating Token Index: 66