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

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

Neuron 2232 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: 0.3747. Min Range: -0.3747

Max Act: 0.3747. Min Act: -0.0000

Data Index: 234768 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1300459 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3432. Min Act: -0.0000

Data Index: 456016 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3417. Min Act: -0.0000

Data Index: 692767 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3014. Min Act: -0.0000

Data Index: 647109 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2900. Min Act: -0.0000

Data Index: 537452 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1246439 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1533592 (Python Code)

Max Activating Token Index: 555

Text #8

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1314089 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1033149 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2174. Min Act: -0.0000

Data Index: 4710 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1053501 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1386288 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1928. Min Act: -0.0000

Data Index: 837414 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1676. Min Act: -0.0000

Data Index: 67657 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1220335 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1443023 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1533266 (Python Code)

Max Activating Token Index: 498

Text #18

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1866. Min Act: -0.0000

Data Index: 812663 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.1879. Min Act: -0.0000

Data Index: 28163 (C4 (Web Text))

Max Activating Token Index: 183