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

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

Neuron 3635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1431719 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1618951 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3577. Min Act: -0.0000

Data Index: 1607183 (Python Code)

Max Activating Token Index: 844

Text #3

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3840. Min Act: -0.0000

Data Index: 1612503 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1612951 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1536302 (Python Code)

Max Activating Token Index: 608

Text #6

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1603189 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3972. Min Act: -0.0000

Data Index: 1587519 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3123. Min Act: -0.0000

Data Index: 1497874 (Python Code)

Max Activating Token Index: 150

Text #9

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1516139 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1550288 (Python Code)

Max Activating Token Index: 130

Text #11

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1613311 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1493213 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.2844. Min Act: -0.0000

Data Index: 1531385 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.2469. Min Act: -0.0000

Data Index: 1435035 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1649617 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.3767. Min Act: -0.0000

Data Index: 1459108 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1615916 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.2542. Min Act: -0.0000

Data Index: 1574288 (Python Code)

Max Activating Token Index: 997

Text #19

Max Range: 1.4869. Min Range: -1.4869

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1375188 (Python Code)

Max Activating Token Index: 231