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

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

Neuron 823 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.6588. Min Act: -0.0001

Data Index: 264210 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.6644. Min Act: -0.0001

Data Index: 1281599 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.6242. Min Act: -0.0001

Data Index: 280734 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.6384. Min Act: -0.0001

Data Index: 297792 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.6319. Min Act: -0.0001

Data Index: 1135896 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.6066. Min Act: -0.0001

Data Index: 198987 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5913. Min Act: -0.0001

Data Index: 294239 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5877. Min Act: -0.0001

Data Index: 834597 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5893. Min Act: -0.0001

Data Index: 267072 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5906. Min Act: -0.0001

Data Index: 1151983 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1281614 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5932. Min Act: -0.0001

Data Index: 1168057 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5982. Min Act: -0.0001

Data Index: 1011769 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1121125 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5859. Min Act: -0.0001

Data Index: 60000 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5743. Min Act: -0.0001

Data Index: 615491 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5726. Min Act: -0.0001

Data Index: 898442 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5887. Min Act: -0.0001

Data Index: 717617 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5773. Min Act: -0.0001

Data Index: 839867 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.6644. Min Range: -0.6644

Max Act: 0.5690. Min Act: -0.0001

Data Index: 895375 (C4 (Web Text))

Max Activating Token Index: 389