Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.2084. Min Act: -0.0003

Data Index: 1652188 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1930. Min Act: -0.0002

Data Index: 1492295 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1869. Min Act: -0.0003

Data Index: 169061 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1591. Min Act: -0.0003

Data Index: 710261 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1542. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 685

Text #5

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1378. Min Act: -0.0002

Data Index: 1601652 (Python Code)

Max Activating Token Index: 96

Text #6

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1439139 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1365. Min Act: -0.0003

Data Index: 1641948 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1324. Min Act: -0.0003

Data Index: 73637 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1246. Min Act: -0.0003

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1438075 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1069. Min Act: -0.0003

Data Index: 1591944 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1021. Min Act: -0.0002

Data Index: 1546413 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1655744 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1507671 (Python Code)

Max Activating Token Index: 112

Text #16

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.0995. Min Act: -0.0002

Data Index: 784054 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1569892 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.0916. Min Act: -0.0003

Data Index: 1548039 (Python Code)

Max Activating Token Index: 24

Text #19

Max Range: 0.2084. Min Range: -0.2084

Max Act: 0.0967. Min Act: -0.0003

Data Index: 493390 (C4 (Web Text))

Max Activating Token Index: 171