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

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

Neuron 4528 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4896. Min Act: -0.0000

Data Index: 1018603 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.2398. Min Act: -0.0000

Data Index: 623694 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1113136 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1018028 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.0623. Min Act: -0.0000

Data Index: 227729 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1269394 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.0945. Min Act: -0.0000

Data Index: 697971 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9811. Min Act: -0.0000

Data Index: 67702 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9868. Min Act: -0.0000

Data Index: 815749 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9716. Min Act: -0.0000

Data Index: 440070 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9934. Min Act: -0.0000

Data Index: 548141 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9247. Min Act: -0.0000

Data Index: 799067 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9012. Min Act: -0.0000

Data Index: 320599 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9770. Min Act: -0.0000

Data Index: 387562 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1048171 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9120. Min Act: -0.0000

Data Index: 281375 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9218. Min Act: -0.0000

Data Index: 658788 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.8614. Min Act: -0.0000

Data Index: 223866 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.9261. Min Act: -0.0000

Data Index: 257167 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.4896. Min Range: -1.4896

Max Act: 0.8293. Min Act: -0.0000

Data Index: 30441 (C4 (Web Text))

Max Activating Token Index: 83