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

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

Neuron 4343 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4663. Min Range: -3.4663

Max Act: 3.4314. Min Act: -0.0000

Data Index: 349706 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 3.4663. Min Range: -3.4663

Max Act: 3.4663. Min Act: -0.0000

Data Index: 1353783 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.9931. Min Act: -0.0000

Data Index: 834412 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.4663. Min Range: -3.4663

Max Act: 3.0920. Min Act: -0.0000

Data Index: 1025555 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.9277. Min Act: -0.0000

Data Index: 971659 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.5946. Min Act: -0.0000

Data Index: 661615 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.9700. Min Act: -0.0000

Data Index: 456824 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.6887. Min Act: -0.0000

Data Index: 36671 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 3.4663. Min Range: -3.4663

Max Act: 3.0359. Min Act: -0.0000

Data Index: 76962 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.4812. Min Act: -0.0000

Data Index: 506099 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.5260. Min Act: -0.0000

Data Index: 642342 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.3389. Min Act: -0.0000

Data Index: 203855 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.5980. Min Act: -0.0000

Data Index: 825459 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.4123. Min Act: -0.0000

Data Index: 1274041 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.4006. Min Act: -0.0000

Data Index: 1111355 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.2876. Min Act: -0.0000

Data Index: 1120459 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.5174. Min Act: -0.0000

Data Index: 1114188 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.2412. Min Act: -0.0000

Data Index: 808680 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.1209. Min Act: -0.0000

Data Index: 445835 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 3.4663. Min Range: -3.4663

Max Act: 2.4550. Min Act: -0.0000

Data Index: 741123 (C4 (Web Text))

Max Activating Token Index: 13