Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 960 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5925. Min Act: -0.0000

Data Index: 431010 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5552. Min Act: -0.0000

Data Index: 564104 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5644. Min Act: -0.0000

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5437. Min Act: -0.0000

Data Index: 43436 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5260. Min Act: -0.0000

Data Index: 359770 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5257. Min Act: -0.0000

Data Index: 860123 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5557. Min Act: -0.0000

Data Index: 468440 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1142154 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5147. Min Act: -0.0000

Data Index: 925837 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4905. Min Act: -0.0000

Data Index: 261277 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1317362 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5068. Min Act: -0.0000

Data Index: 540727 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5662. Min Act: -0.0000

Data Index: 487664 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5043. Min Act: -0.0000

Data Index: 583084 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1153881 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4791. Min Act: -0.0000

Data Index: 445019 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.5122. Min Act: -0.0000

Data Index: 111378 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1091715 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4709. Min Act: -0.0000

Data Index: 265960 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.5925. Min Range: -0.5925

Max Act: 0.4956. Min Act: -0.0000

Data Index: 823296 (C4 (Web Text))

Max Activating Token Index: 344