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

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

Neuron 5981 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: 1.0630. Min Range: -1.0630

Max Act: 1.0630. Min Act: -0.0000

Data Index: 662246 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9456. Min Act: -0.0000

Data Index: 1274827 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9356. Min Act: -0.0000

Data Index: 884834 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.9265. Min Act: -0.0000

Data Index: 126822 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8856. Min Act: -0.0000

Data Index: 304581 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8789. Min Act: -0.0000

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7835. Min Act: -0.0000

Data Index: 544968 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8658. Min Act: -0.0000

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8610. Min Act: -0.0000

Data Index: 100855 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8451. Min Act: -0.0000

Data Index: 129834 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7889. Min Act: -0.0000

Data Index: 428983 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8347. Min Act: -0.0000

Data Index: 350974 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8436. Min Act: -0.0000

Data Index: 83804 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8937. Min Act: -0.0000

Data Index: 84588 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8280. Min Act: -0.0000

Data Index: 614903 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.7884. Min Act: -0.0000

Data Index: 956882 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8838. Min Act: -0.0000

Data Index: 598916 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.0630. Min Range: -1.0630

Max Act: 0.8027. Min Act: -0.0000

Data Index: 418888 (C4 (Web Text))

Max Activating Token Index: 150