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

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

Neuron 3598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1340080 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3624. Min Act: -0.0000

Data Index: 965934 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1301797 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3204. Min Act: -0.0001

Data Index: 119058 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3223. Min Act: -0.0000

Data Index: 763357 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3106. Min Act: -0.0001

Data Index: 964377 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3282. Min Act: -0.0001

Data Index: 708837 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1302894 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3115. Min Act: -0.0001

Data Index: 234460 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3012. Min Act: -0.0001

Data Index: 699536 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2888. Min Act: -0.0001

Data Index: 321551 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2914. Min Act: -0.0001

Data Index: 839915 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2891. Min Act: -0.0001

Data Index: 539808 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1290933 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1158753 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2638. Min Act: -0.0001

Data Index: 438002 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2790. Min Act: -0.0001

Data Index: 231876 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2761. Min Act: -0.0001

Data Index: 100247 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2709. Min Act: -0.0000

Data Index: 481777 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1260558 (C4 (Web Text))

Max Activating Token Index: 521