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

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

Neuron 586 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6340. Min Act: -0.0001

Data Index: 1464795 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.9213. Min Act: -0.0001

Data Index: 1612708 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.6715. Min Act: -0.0001

Data Index: 1617162 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.4083. Min Act: -0.0001

Data Index: 1562873 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.7465. Min Act: -0.0001

Data Index: 1597739 (Python Code)

Max Activating Token Index: 526

Text #5

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.4365. Min Act: -0.0001

Data Index: 1655179 (Python Code)

Max Activating Token Index: 42

Text #6

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.1827. Min Act: -0.0001

Data Index: 1463260 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.2911. Min Act: -0.0001

Data Index: 1561677 (Python Code)

Max Activating Token Index: 332

Text #8

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.1275. Min Act: -0.0001

Data Index: 1652762 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.4153. Min Act: -0.0001

Data Index: 1411545 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.4147. Min Act: -0.0001

Data Index: 1455855 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.3994. Min Act: -0.0001

Data Index: 1605598 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.2793. Min Act: -0.0001

Data Index: 1540248 (Python Code)

Max Activating Token Index: 192

Text #13

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.0944. Min Act: -0.0001

Data Index: 1490969 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.2134. Min Act: -0.0001

Data Index: 1485224 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.0614. Min Act: -0.0001

Data Index: 1441194 (Python Code)

Max Activating Token Index: 521

Text #16

Max Range: 3.9213. Min Range: -3.9213

Max Act: 2.7794. Min Act: -0.0001

Data Index: 1534493 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.2634. Min Act: -0.0001

Data Index: 1451482 (Python Code)

Max Activating Token Index: 566

Text #18

Max Range: 3.9213. Min Range: -3.9213

Max Act: 3.0761. Min Act: -0.0001

Data Index: 1378639 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 3.9213. Min Range: -3.9213

Max Act: 2.6405. Min Act: -0.0001

Data Index: 1648546 (Python Code)

Max Activating Token Index: 301