Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 750 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.7298. Min Act: -0.0003

Data Index: 1509847 (Python Code)

Max Activating Token Index: 867

Text #1

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.7566. Min Act: -0.0003

Data Index: 1494036 (Python Code)

Max Activating Token Index: 700

Text #2

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6957. Min Act: -0.0003

Data Index: 1398608 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.7137. Min Act: -0.0003

Data Index: 1552790 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.7285. Min Act: -0.0003

Data Index: 1563862 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6702. Min Act: -0.0003

Data Index: 1597910 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6361. Min Act: -0.0003

Data Index: 1590693 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6302. Min Act: -0.0003

Data Index: 1439887 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6157. Min Act: -0.0003

Data Index: 1388893 (Python Code)

Max Activating Token Index: 909

Text #9

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6255. Min Act: -0.0003

Data Index: 1596294 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6347. Min Act: -0.0003

Data Index: 1547432 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.7426. Min Act: -0.0003

Data Index: 1640554 (Python Code)

Max Activating Token Index: 871

Text #12

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.5833. Min Act: -0.0003

Data Index: 1572272 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6189. Min Act: -0.0003

Data Index: 1649640 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6510. Min Act: -0.0003

Data Index: 1638548 (Python Code)

Max Activating Token Index: 786

Text #15

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6051. Min Act: -0.0003

Data Index: 1628352 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6195. Min Act: -0.0003

Data Index: 1609053 (Python Code)

Max Activating Token Index: 651

Text #17

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6195. Min Act: -0.0003

Data Index: 1524581 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6190. Min Act: -0.0003

Data Index: 1634839 (Python Code)

Max Activating Token Index: 264

Text #19

Max Range: 0.7566. Min Range: -0.7566

Max Act: 0.6166. Min Act: -0.0003

Data Index: 1605097 (Python Code)

Max Activating Token Index: 372