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

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

Neuron 592 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0001. Min Range: -2.0001

Max Act: 2.0001. Min Act: -0.0000

Data Index: 742068 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4696. Min Act: -0.0000

Data Index: 34110 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1103818 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4486. Min Act: -0.0000

Data Index: 781012 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4744. Min Act: -0.0000

Data Index: 135382 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3559. Min Act: -0.0000

Data Index: 234214 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4303. Min Act: -0.0000

Data Index: 1107140 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1063273 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1123256 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1160132 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4474. Min Act: -0.0000

Data Index: 1309813 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3659. Min Act: -0.0000

Data Index: 312190 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3261. Min Act: -0.0000

Data Index: 831918 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.2841. Min Act: -0.0000

Data Index: 960119 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1015697 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4243. Min Act: -0.0000

Data Index: 946065 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3322. Min Act: -0.0000

Data Index: 230275 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1065700 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.2491. Min Act: -0.0000

Data Index: 419714 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3147. Min Act: -0.0000

Data Index: 862474 (C4 (Web Text))

Max Activating Token Index: 37