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

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

Neuron 3808 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.6425. Min Act: -0.0002

Data Index: 90802 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.6025. Min Act: -0.0002

Data Index: 47291 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.6155. Min Act: -0.0002

Data Index: 823695 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5663. Min Act: -0.0002

Data Index: 883966 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5313. Min Act: -0.0002

Data Index: 536905 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5451. Min Act: -0.0002

Data Index: 1109731 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5248. Min Act: -0.0002

Data Index: 340236 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5943. Min Act: -0.0002

Data Index: 631153 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5291. Min Act: -0.0002

Data Index: 732558 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5702. Min Act: -0.0002

Data Index: 413552 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5376. Min Act: -0.0002

Data Index: 1322591 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5035. Min Act: -0.0002

Data Index: 890868 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5168. Min Act: -0.0002

Data Index: 549614 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5249. Min Act: -0.0002

Data Index: 1286298 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5093. Min Act: -0.0002

Data Index: 1309419 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5091. Min Act: -0.0002

Data Index: 331745 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.5388. Min Act: -0.0002

Data Index: 14973 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4901. Min Act: -0.0002

Data Index: 704229 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4857. Min Act: -0.0002

Data Index: 485167 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.6425. Min Range: -0.6425

Max Act: 0.4867. Min Act: -0.0002

Data Index: 46489 (C4 (Web Text))

Max Activating Token Index: 670