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

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

Neuron 1271 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.8403. Min Act: -0.0000

Data Index: 42897 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.5094. Min Act: -0.0000

Data Index: 64707 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.6702. Min Act: -0.0000

Data Index: 361191 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4743. Min Act: -0.0000

Data Index: 1286167 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.5026. Min Act: -0.0000

Data Index: 435717 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4136. Min Act: -0.0000

Data Index: 675149 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.5091. Min Act: -0.0000

Data Index: 681885 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3619. Min Act: -0.0000

Data Index: 808169 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1277812 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3324. Min Act: -0.0000

Data Index: 535442 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1119691 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4743. Min Act: -0.0000

Data Index: 136943 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3792. Min Act: -0.0000

Data Index: 639568 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3809. Min Act: -0.0000

Data Index: 835235 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3684. Min Act: -0.0000

Data Index: 977370 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3803. Min Act: -0.0000

Data Index: 675531 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.4428. Min Act: -0.0000

Data Index: 804101 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.2958. Min Act: -0.0000

Data Index: 523894 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.3504. Min Act: -0.0000

Data Index: 143593 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.8403. Min Range: -1.8403

Max Act: 1.2000. Min Act: -0.0000

Data Index: 523462 (C4 (Web Text))

Max Activating Token Index: 418