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

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

Neuron 1717 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.5547. Min Act: -0.0001

Data Index: 615820 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.4109. Min Act: -0.0001

Data Index: 1128669 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3585. Min Act: -0.0001

Data Index: 912455 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2795. Min Act: -0.0001

Data Index: 650954 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2772. Min Act: -0.0001

Data Index: 795801 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1754. Min Act: -0.0001

Data Index: 18130 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1998. Min Act: -0.0001

Data Index: 1143259 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1379. Min Act: -0.0001

Data Index: 1249122 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1581. Min Act: -0.0001

Data Index: 873819 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2131. Min Act: -0.0001

Data Index: 1287658 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1491. Min Act: -0.0001

Data Index: 237687 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1269. Min Act: -0.0001

Data Index: 180238 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0984. Min Act: -0.0001

Data Index: 195059 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1000. Min Act: -0.0001

Data Index: 612873 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0645. Min Act: -0.0001

Data Index: 324386 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0656. Min Act: -0.0001

Data Index: 1170105 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0089. Min Act: -0.0001

Data Index: 256365 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0832. Min Act: -0.0001

Data Index: 709657 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 1.5547. Min Range: -1.5547

Max Act: 0.9798. Min Act: -0.0001

Data Index: 973225 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0623. Min Act: -0.0001

Data Index: 908258 (C4 (Web Text))

Max Activating Token Index: 369