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

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

Neuron 3594 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: 0.7202. Min Range: -0.7202

Max Act: 0.6816. Min Act: -0.0000

Data Index: 549589 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.7202. Min Act: -0.0000

Data Index: 442072 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5898. Min Act: -0.0000

Data Index: 911319 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6470. Min Act: -0.0000

Data Index: 256554 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6009. Min Act: -0.0000

Data Index: 467463 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5928. Min Act: -0.0000

Data Index: 718594 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6116. Min Act: -0.0000

Data Index: 899443 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6206. Min Act: -0.0000

Data Index: 101813 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1216303 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6453. Min Act: -0.0000

Data Index: 956507 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6227. Min Act: -0.0000

Data Index: 913488 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1258224 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5932. Min Act: -0.0000

Data Index: 514466 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5959. Min Act: -0.0000

Data Index: 508334 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5870. Min Act: -0.0000

Data Index: 581989 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5572. Min Act: -0.0000

Data Index: 271849 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5513. Min Act: -0.0000

Data Index: 757378 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5470. Min Act: -0.0000

Data Index: 368904 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5542. Min Act: -0.0000

Data Index: 369229 (C4 (Web Text))

Max Activating Token Index: 700