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

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

Neuron 2678 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.7545. Min Act: -0.0000

Data Index: 538616 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6837. Min Act: -0.0000

Data Index: 976250 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6128. Min Act: -0.0000

Data Index: 69563 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.6060. Min Act: -0.0000

Data Index: 828362 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1136371 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1038904 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4995. Min Act: -0.0000

Data Index: 21970 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5018. Min Act: -0.0000

Data Index: 265863 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.5128. Min Act: -0.0000

Data Index: 162431 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1180266 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4838. Min Act: -0.0000

Data Index: 937426 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4827. Min Act: -0.0000

Data Index: 601116 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4835. Min Act: -0.0000

Data Index: 516140 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4915. Min Act: -0.0000

Data Index: 551897 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4726. Min Act: -0.0000

Data Index: 740580 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4484. Min Act: -0.0000

Data Index: 207638 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4435. Min Act: -0.0000

Data Index: 71485 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1143247 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4785. Min Act: -0.0000

Data Index: 409615 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.7545. Min Range: -0.7545

Max Act: 0.4451. Min Act: -0.0000

Data Index: 665528 (C4 (Web Text))

Max Activating Token Index: 661