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

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

Neuron 4347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1743. Min Range: -1.1743

Max Act: 1.1743. Min Act: -0.0001

Data Index: 305856 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.1743. Min Range: -1.1743

Max Act: 1.0799. Min Act: -0.0001

Data Index: 320389 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.1743. Min Range: -1.1743

Max Act: 1.0748. Min Act: -0.0001

Data Index: 61074 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9771. Min Act: -0.0001

Data Index: 25082 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9692. Min Act: -0.0001

Data Index: 414877 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9670. Min Act: -0.0001

Data Index: 295893 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9107. Min Act: -0.0001

Data Index: 440723 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9655. Min Act: -0.0001

Data Index: 775227 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9621. Min Act: -0.0001

Data Index: 1021924 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9507. Min Act: -0.0001

Data Index: 1232916 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9496. Min Act: -0.0001

Data Index: 475876 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.7942. Min Act: -0.0001

Data Index: 1008070 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1043122 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9188. Min Act: -0.0001

Data Index: 155777 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1117494 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.8491. Min Act: -0.0001

Data Index: 633056 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.7748. Min Act: -0.0001

Data Index: 79545 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9010. Min Act: -0.0001

Data Index: 355250 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.9033. Min Act: -0.0001

Data Index: 1257640 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 1.1743. Min Range: -1.1743

Max Act: 0.8702. Min Act: -0.0001

Data Index: 1334682 (C4 (Web Text))

Max Activating Token Index: 517