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

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

Neuron 4704 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1005094 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1352662 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.6386. Min Act: -0.0000

Data Index: 679591 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.6557. Min Act: -0.0000

Data Index: 454385 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1165333 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1241251 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5888. Min Act: -0.0000

Data Index: 563248 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.6049. Min Act: -0.0000

Data Index: 115028 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5197. Min Act: -0.0000

Data Index: 152866 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5434. Min Act: -0.0000

Data Index: 989062 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5236. Min Act: -0.0000

Data Index: 370696 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1217122 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1237476 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4916. Min Act: -0.0000

Data Index: 264641 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1491798 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4989. Min Act: -0.0000

Data Index: 334323 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1656015 (Python Code)

Max Activating Token Index: 304

Text #17

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1113760 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1132745 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.7132. Min Range: -0.7132

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1475347 (Python Code)

Max Activating Token Index: 855