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

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

Neuron 3186 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9115. Min Range: -5.9115

Max Act: 5.9115. Min Act: -0.0000

Data Index: 444443 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 5.9115. Min Range: -5.9115

Max Act: 4.0438. Min Act: -0.0001

Data Index: 390314 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 5.9115. Min Range: -5.9115

Max Act: 4.0053. Min Act: -0.0000

Data Index: 845260 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.7909. Min Act: -0.0001

Data Index: 425059 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.6785. Min Act: -0.0001

Data Index: 662175 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.4130. Min Act: -0.0000

Data Index: 671451 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.2468. Min Act: -0.0000

Data Index: 76495 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.1135. Min Act: -0.0000

Data Index: 34145 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.0802. Min Act: -0.0000

Data Index: 42716 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.2330. Min Act: -0.0000

Data Index: 329366 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.0800. Min Act: -0.0001

Data Index: 595489 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.3331. Min Act: -0.0001

Data Index: 1299373 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.2924. Min Act: -0.0000

Data Index: 361176 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 5.9115. Min Range: -5.9115

Max Act: 2.9846. Min Act: -0.0000

Data Index: 510581 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.1063. Min Act: -0.0000

Data Index: 576288 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.2238. Min Act: -0.0001

Data Index: 375363 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.0757. Min Act: -0.0000

Data Index: 673198 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.0650. Min Act: -0.0001

Data Index: 701853 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.0547. Min Act: -0.0000

Data Index: 972240 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 5.9115. Min Range: -5.9115

Max Act: 3.0395. Min Act: -0.0001

Data Index: 933651 (C4 (Web Text))

Max Activating Token Index: 610