Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0938. Min Act: -0.0001

Data Index: 502139 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 1.0938. Min Range: -1.0938

Max Act: 1.0713. Min Act: -0.0001

Data Index: 447742 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9969. Min Act: -0.0001

Data Index: 1116519 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9734. Min Act: -0.0001

Data Index: 928682 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.9436. Min Act: -0.0001

Data Index: 925056 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8496. Min Act: -0.0001

Data Index: 1002724 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8984. Min Act: -0.0001

Data Index: 745534 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8477. Min Act: -0.0001

Data Index: 140473 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1256791 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8056. Min Act: -0.0001

Data Index: 1030095 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7948. Min Act: -0.0001

Data Index: 474932 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.8384. Min Act: -0.0001

Data Index: 1164405 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7134. Min Act: -0.0001

Data Index: 711947 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.7029. Min Act: -0.0001

Data Index: 1106561 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.6038. Min Act: -0.0001

Data Index: 1135508 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.6744. Min Act: -0.0001

Data Index: 452254 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.6678. Min Act: -0.0001

Data Index: 68698 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.6801. Min Act: -0.0001

Data Index: 634172 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.6816. Min Act: -0.0001

Data Index: 411201 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.0938. Min Range: -1.0938

Max Act: 0.6634. Min Act: -0.0001

Data Index: 225362 (C4 (Web Text))

Max Activating Token Index: 158