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

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

Neuron 1509 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.8925. Min Act: -0.0000

Data Index: 398971 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1163532 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.4581. Min Act: -0.0001

Data Index: 685237 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3848. Min Act: -0.0000

Data Index: 687112 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3857. Min Act: -0.0001

Data Index: 96266 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3673. Min Act: -0.0000

Data Index: 372472 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3649. Min Act: -0.0000

Data Index: 879002 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3738. Min Act: -0.0000

Data Index: 217595 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3864. Min Act: -0.0001

Data Index: 83107 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1123973 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3706. Min Act: -0.0001

Data Index: 600619 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1069031 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3621. Min Act: -0.0001

Data Index: 161257 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3678. Min Act: -0.0001

Data Index: 292142 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3578. Min Act: -0.0001

Data Index: 98613 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3556. Min Act: -0.0001

Data Index: 809830 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3530. Min Act: -0.0000

Data Index: 538777 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3776. Min Act: -0.0001

Data Index: 816097 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3434. Min Act: -0.0000

Data Index: 713539 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.8925. Min Range: -0.8925

Max Act: 0.3588. Min Act: -0.0001

Data Index: 195577 (C4 (Web Text))

Max Activating Token Index: 772