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

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

Neuron 3797 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1882. Min Range: -2.1882

Max Act: 2.1882. Min Act: -0.0000

Data Index: 674600 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.9468. Min Act: -0.0000

Data Index: 796118 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.8593. Min Act: -0.0000

Data Index: 1157405 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.4532. Min Act: -0.0000

Data Index: 913235 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1082031 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1083675 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.3554. Min Act: -0.0000

Data Index: 1314716 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.4284. Min Act: -0.0000

Data Index: 178561 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.3383. Min Act: -0.0000

Data Index: 438585 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.3311. Min Act: -0.0000

Data Index: 502753 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2892. Min Act: -0.0000

Data Index: 937388 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2113. Min Act: -0.0000

Data Index: 1249005 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2728. Min Act: -0.0000

Data Index: 639954 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2673. Min Act: -0.0000

Data Index: 937823 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2646. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2300. Min Act: -0.0000

Data Index: 1174437 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.1952. Min Act: -0.0000

Data Index: 153745 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.2008. Min Act: -0.0000

Data Index: 675321 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 2.1882. Min Range: -2.1882

Max Act: 1.1711. Min Act: -0.0000

Data Index: 1082762 (C4 (Web Text))

Max Activating Token Index: 184