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

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

Neuron 3731 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1402411 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1594981 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1649276 (Python Code)

Max Activating Token Index: 46

Text #3

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1497518 (Python Code)

Max Activating Token Index: 429

Text #4

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1652730 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5013. Min Act: -0.0001

Data Index: 1391854 (Python Code)

Max Activating Token Index: 962

Text #6

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1433855 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1489694 (Python Code)

Max Activating Token Index: 455

Text #8

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1496066 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1646000 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1440033 (Python Code)

Max Activating Token Index: 944

Text #11

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1520148 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1495752 (Python Code)

Max Activating Token Index: 641

Text #13

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1368438 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1644943 (Python Code)

Max Activating Token Index: 649

Text #15

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1496939 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1594401 (Python Code)

Max Activating Token Index: 733

Text #17

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1410606 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1640831 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1381236 (Python Code)

Max Activating Token Index: 325