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

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

Neuron 3909 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4901. Min Act: -0.0000

Data Index: 741939 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4091. Min Act: -0.0000

Data Index: 663055 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1251944 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3813. Min Act: -0.0000

Data Index: 547686 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3720. Min Act: -0.0000

Data Index: 201974 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3148. Min Act: -0.0000

Data Index: 918148 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1154914 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3862. Min Act: -0.0000

Data Index: 423064 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1423964 (Python Code)

Max Activating Token Index: 249

Text #9

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3230. Min Act: -0.0000

Data Index: 306341 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1049921 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3493. Min Act: -0.0000

Data Index: 313466 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3190. Min Act: -0.0000

Data Index: 831013 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1364721 (Python Code)

Max Activating Token Index: 261

Text #14

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3417. Min Act: -0.0000

Data Index: 98394 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1591309 (Python Code)

Max Activating Token Index: 544

Text #16

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3073. Min Act: -0.0000

Data Index: 309108 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1002259 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3029. Min Act: -0.0000

Data Index: 899530 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.4901. Min Range: -0.4901

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1382187 (Python Code)

Max Activating Token Index: 376