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

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

Neuron 3791 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: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0001

Data Index: 365455 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2144. Min Act: -0.0001

Data Index: 649175 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2201. Min Act: -0.0001

Data Index: 770034 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1940. Min Act: -0.0001

Data Index: 228595 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2062. Min Act: -0.0001

Data Index: 700182 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2002. Min Act: -0.0001

Data Index: 515213 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1969. Min Act: -0.0001

Data Index: 167735 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2100. Min Act: -0.0001

Data Index: 371612 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1974. Min Act: -0.0001

Data Index: 402835 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1153612 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1176496 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1869. Min Act: -0.0001

Data Index: 598176 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1790. Min Act: -0.0001

Data Index: 490592 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1920. Min Act: -0.0001

Data Index: 793891 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1928. Min Act: -0.0001

Data Index: 718510 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1844. Min Act: -0.0001

Data Index: 665893 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1344998 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1907. Min Act: -0.0001

Data Index: 364315 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1661. Min Act: -0.0001

Data Index: 496126 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1826. Min Act: -0.0001

Data Index: 486703 (C4 (Web Text))

Max Activating Token Index: 509