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

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

Neuron 1136 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: 0.9422. Min Range: -0.9422

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1219171 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8608. Min Act: -0.0000

Data Index: 317577 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8626. Min Act: -0.0000

Data Index: 846676 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8290. Min Act: -0.0000

Data Index: 714835 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7305. Min Act: -0.0000

Data Index: 582903 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1123130 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7561. Min Act: -0.0000

Data Index: 97609 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7557. Min Act: -0.0000

Data Index: 281700 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1041721 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7288. Min Act: -0.0000

Data Index: 525555 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7553. Min Act: -0.0000

Data Index: 503200 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1032576 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7504. Min Act: -0.0000

Data Index: 409121 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6894. Min Act: -0.0000

Data Index: 277188 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1272102 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6917. Min Act: -0.0000

Data Index: 630201 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7126. Min Act: -0.0000

Data Index: 974792 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7147. Min Act: -0.0000

Data Index: 610159 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6868. Min Act: -0.0000

Data Index: 841657 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.6861. Min Act: -0.0000

Data Index: 715481 (C4 (Web Text))

Max Activating Token Index: 512