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

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

Neuron 2030 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2486. Min Range: -1.2486

Max Act: 1.2486. Min Act: -0.0000

Data Index: 855635 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.2486. Min Range: -1.2486

Max Act: 1.1891. Min Act: -0.0000

Data Index: 798073 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 1.2486. Min Range: -1.2486

Max Act: 1.1322. Min Act: -0.0000

Data Index: 344572 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.2486. Min Range: -1.2486

Max Act: 1.0275. Min Act: -0.0000

Data Index: 832097 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8775. Min Act: -0.0000

Data Index: 503698 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8318. Min Act: -0.0000

Data Index: 121118 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.9414. Min Act: -0.0000

Data Index: 329169 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8303. Min Act: -0.0000

Data Index: 305248 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1238027 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.9539. Min Act: -0.0000

Data Index: 315963 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8562. Min Act: -0.0000

Data Index: 745252 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8186. Min Act: -0.0000

Data Index: 430526 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8258. Min Act: -0.0000

Data Index: 399414 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.7021. Min Act: -0.0000

Data Index: 271113 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8208. Min Act: -0.0001

Data Index: 225726 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.7812. Min Act: -0.0000

Data Index: 815042 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.8289. Min Act: -0.0000

Data Index: 633461 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.7907. Min Act: -0.0000

Data Index: 353928 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.7560. Min Act: -0.0000

Data Index: 708 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 1.2486. Min Range: -1.2486

Max Act: 0.7418. Min Act: -0.0000

Data Index: 277347 (C4 (Web Text))

Max Activating Token Index: 256