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

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

Neuron 3151 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: 1.0005. Min Range: -1.0005

Max Act: 1.0005. Min Act: -0.0000

Data Index: 832671 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7811. Min Act: -0.0000

Data Index: 473862 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7547. Min Act: -0.0000

Data Index: 212210 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7550. Min Act: -0.0000

Data Index: 15579 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.7148. Min Act: -0.0000

Data Index: 924087 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.6906. Min Act: -0.0000

Data Index: 607944 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1294723 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5653. Min Act: -0.0000

Data Index: 775058 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5996. Min Act: -0.0000

Data Index: 870694 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5843. Min Act: -0.0000

Data Index: 942368 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5819. Min Act: -0.0000

Data Index: 389477 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5781. Min Act: -0.0000

Data Index: 727734 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1273238 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5748. Min Act: -0.0000

Data Index: 59654 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5164. Min Act: -0.0000

Data Index: 150858 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5685. Min Act: -0.0000

Data Index: 182988 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5832. Min Act: -0.0000

Data Index: 830547 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5620. Min Act: -0.0000

Data Index: 247503 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5569. Min Act: -0.0000

Data Index: 198527 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.5547. Min Act: -0.0000

Data Index: 541398 (C4 (Web Text))

Max Activating Token Index: 61