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

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

Neuron 599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0871. Min Act: -0.0000

Data Index: 963347 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0831. Min Act: -0.0000

Data Index: 137979 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0784. Min Act: -0.0000

Data Index: 359900 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1425994 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1113132 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0772. Min Act: -0.0000

Data Index: 983138 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0714. Min Act: -0.0000

Data Index: 249858 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1180318 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0759. Min Act: -0.0000

Data Index: 374084 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0710. Min Act: -0.0000

Data Index: 466156 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0673. Min Act: -0.0000

Data Index: 928337 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0710. Min Act: -0.0000

Data Index: 530809 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1261859 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0654. Min Act: -0.0000

Data Index: 1175994 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0696. Min Act: -0.0000

Data Index: 382280 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1531111 (Python Code)

Max Activating Token Index: 327

Text #16

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1130165 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0664. Min Act: -0.0000

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0666. Min Act: -0.0000

Data Index: 581408 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0871. Min Range: -0.0871

Max Act: 0.0662. Min Act: -0.0000

Data Index: 635869 (C4 (Web Text))

Max Activating Token Index: 1007