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

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

Neuron 2644 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.8201. Min Act: -0.0000

Data Index: 1565769 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.3327. Min Act: -0.0000

Data Index: 1609143 (Python Code)

Max Activating Token Index: 522

Text #2

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.4207. Min Act: -0.0000

Data Index: 1392554 (Python Code)

Max Activating Token Index: 617

Text #3

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.4148. Min Act: -0.0001

Data Index: 1433386 (Python Code)

Max Activating Token Index: 585

Text #4

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.2601. Min Act: -0.0000

Data Index: 1559728 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.9706. Min Act: -0.0001

Data Index: 1454344 (Python Code)

Max Activating Token Index: 546

Text #6

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.1469. Min Act: -0.0000

Data Index: 1424884 (Python Code)

Max Activating Token Index: 931

Text #7

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.9536. Min Act: -0.0001

Data Index: 1468551 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.9290. Min Act: -0.0000

Data Index: 1309619 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.2676. Min Act: -0.0001

Data Index: 1402620 (Python Code)

Max Activating Token Index: 991

Text #10

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.0401. Min Act: -0.0000

Data Index: 1431282 (Python Code)

Max Activating Token Index: 1014

Text #11

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1382642 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.8080. Min Act: -0.0000

Data Index: 1632430 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.8269. Min Act: -0.0001

Data Index: 1503171 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.9400. Min Act: -0.0000

Data Index: 1598575 (Python Code)

Max Activating Token Index: 550

Text #15

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.8960. Min Act: -0.0000

Data Index: 1595941 (Python Code)

Max Activating Token Index: 1017

Text #16

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.8285. Min Act: -0.0000

Data Index: 1598570 (Python Code)

Max Activating Token Index: 444

Text #17

Max Range: 2.8201. Min Range: -2.8201

Max Act: 2.0840. Min Act: -0.0001

Data Index: 1640990 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.8505. Min Act: -0.0000

Data Index: 728186 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.8201. Min Range: -2.8201

Max Act: 1.8512. Min Act: -0.0001

Data Index: 1579159 (Python Code)

Max Activating Token Index: 576