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

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

Neuron 1627 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7814. Min Range: -2.7814

Max Act: 2.7814. Min Act: -0.0000

Data Index: 948035 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 2.7814. Min Range: -2.7814

Max Act: 2.2128. Min Act: -0.0000

Data Index: 472836 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.6718. Min Act: -0.0000

Data Index: 672913 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.7291. Min Act: -0.0000

Data Index: 1127371 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.6917. Min Act: -0.0000

Data Index: 54584 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.6261. Min Act: -0.0000

Data Index: 754581 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1161921 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.5512. Min Act: -0.0000

Data Index: 11280 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.5138. Min Act: -0.0000

Data Index: 662537 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.4366. Min Act: -0.0000

Data Index: 208937 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.3430. Min Act: -0.0000

Data Index: 311810 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.4979. Min Act: -0.0000

Data Index: 62626 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.6159. Min Act: -0.0000

Data Index: 992688 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.3706. Min Act: -0.0000

Data Index: 906785 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.3827. Min Act: -0.0000

Data Index: 1498234 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.3694. Min Act: -0.0000

Data Index: 405247 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1485185 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.4378. Min Act: -0.0000

Data Index: 1254821 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.2803. Min Act: -0.0000

Data Index: 717473 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 2.7814. Min Range: -2.7814

Max Act: 1.3483. Min Act: -0.0000

Data Index: 965582 (C4 (Web Text))

Max Activating Token Index: 404