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

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

Neuron 3870 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: 2.9146. Min Range: -2.9146

Max Act: 2.7985. Min Act: -0.0000

Data Index: 692778 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.7726. Min Act: 0.0000

Data Index: 16368 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.7648. Min Act: -0.0000

Data Index: 442148 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.7379. Min Act: -0.0000

Data Index: 305293 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.6035. Min Act: -0.0000

Data Index: 931638 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.6726. Min Act: -0.0000

Data Index: 1301289 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.6732. Min Act: 0.0000

Data Index: 225758 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.5220. Min Act: -0.0000

Data Index: 510895 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.6152. Min Act: -0.0000

Data Index: 678509 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.9146. Min Act: -0.0000

Data Index: 568921 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.6069. Min Act: -0.0000

Data Index: 735660 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.6072. Min Act: -0.0000

Data Index: 777548 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.7108. Min Act: -0.0000

Data Index: 1127979 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.5773. Min Act: -0.0000

Data Index: 342026 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.4345. Min Act: -0.0000

Data Index: 882460 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.5487. Min Act: -0.0000

Data Index: 386680 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.5139. Min Act: -0.0000

Data Index: 391277 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.5092. Min Act: -0.0000

Data Index: 1404387 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.5928. Min Act: -0.0000

Data Index: 673490 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 2.9146. Min Range: -2.9146

Max Act: 2.4588. Min Act: -0.0000

Data Index: 1145629 (C4 (Web Text))

Max Activating Token Index: 20