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

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

Neuron 3923 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.8987. Min Act: -0.0000

Data Index: 146223 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 4.0539. Min Range: -4.0539

Max Act: 4.0539. Min Act: -0.0000

Data Index: 831578 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4375. Min Act: -0.0000

Data Index: 1063265 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.9344. Min Act: -0.0000

Data Index: 1113495 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.6360. Min Act: -0.0000

Data Index: 39247 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4513. Min Act: -0.0000

Data Index: 698009 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4340. Min Act: -0.0000

Data Index: 412957 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.5911. Min Act: -0.0000

Data Index: 1035245 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.5814. Min Act: -0.0000

Data Index: 1096851 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.5918. Min Act: -0.0000

Data Index: 842803 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4091. Min Act: -0.0000

Data Index: 914837 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4409. Min Act: -0.0000

Data Index: 348166 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.2786. Min Act: -0.0000

Data Index: 1084239 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4531. Min Act: -0.0000

Data Index: 823678 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.5940. Min Act: -0.0000

Data Index: 1210964 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.7655. Min Act: -0.0000

Data Index: 376285 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.5753. Min Act: -0.0000

Data Index: 1308750 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4189. Min Act: -0.0000

Data Index: 1099857 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.4108. Min Act: -0.0000

Data Index: 879628 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 4.0539. Min Range: -4.0539

Max Act: 3.3859. Min Act: -0.0000

Data Index: 346438 (C4 (Web Text))

Max Activating Token Index: 71