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

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

Neuron 3207 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.8311. Min Act: -0.0001

Data Index: 1585370 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.6761. Min Act: -0.0001

Data Index: 1590984 (Python Code)

Max Activating Token Index: 897

Text #2

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.6309. Min Act: -0.0001

Data Index: 1532950 (Python Code)

Max Activating Token Index: 763

Text #3

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.6001. Min Act: -0.0001

Data Index: 1397935 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.5769. Min Act: -0.0001

Data Index: 1619572 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4778. Min Act: -0.0001

Data Index: 1502322 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3689. Min Act: -0.0001

Data Index: 1438714 (Python Code)

Max Activating Token Index: 442

Text #7

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3676. Min Act: -0.0001

Data Index: 1490325 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3828. Min Act: -0.0001

Data Index: 1605300 (Python Code)

Max Activating Token Index: 457

Text #9

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3822. Min Act: -0.0001

Data Index: 1518082 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3884. Min Act: -0.0001

Data Index: 1534071 (Python Code)

Max Activating Token Index: 409

Text #11

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3772. Min Act: -0.0001

Data Index: 1540874 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.4481. Min Act: -0.0001

Data Index: 1485614 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.2625. Min Act: -0.0001

Data Index: 1405143 (Python Code)

Max Activating Token Index: 312

Text #14

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.2750. Min Act: -0.0001

Data Index: 1375044 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3858. Min Act: -0.0001

Data Index: 1510497 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3061. Min Act: -0.0001

Data Index: 1596295 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.3265. Min Act: -0.0001

Data Index: 1539131 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.2242. Min Act: -0.0001

Data Index: 1440236 (Python Code)

Max Activating Token Index: 898

Text #19

Max Range: 1.8311. Min Range: -1.8311

Max Act: 1.2847. Min Act: -0.0001

Data Index: 1547870 (Python Code)

Max Activating Token Index: 109