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

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

Neuron 2531 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8369. Min Act: -0.0001

Data Index: 1460371 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8864. Min Act: -0.0001

Data Index: 1421077 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7867. Min Act: -0.0001

Data Index: 1546650 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8283. Min Act: -0.0001

Data Index: 876264 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.8528. Min Act: -0.0001

Data Index: 1537398 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7880. Min Act: -0.0001

Data Index: 978401 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7785. Min Act: -0.0001

Data Index: 1384446 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7620. Min Act: -0.0001

Data Index: 673330 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7470. Min Act: -0.0001

Data Index: 1585278 (Python Code)

Max Activating Token Index: 371

Text #9

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7389. Min Act: -0.0001

Data Index: 1426336 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1558263 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1633746 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.7193. Min Act: -0.0001

Data Index: 1630535 (Python Code)

Max Activating Token Index: 637

Text #13

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1623475 (Python Code)

Max Activating Token Index: 722

Text #14

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1442674 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6868. Min Act: -0.0001

Data Index: 269190 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1342541 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1557798 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6972. Min Act: -0.0001

Data Index: 1512584 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 0.8864. Min Range: -0.8864

Max Act: 0.6691. Min Act: -0.0001

Data Index: 661531 (C4 (Web Text))

Max Activating Token Index: 156