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

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

Neuron 3747 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1269256 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7271. Min Act: -0.0000

Data Index: 900130 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6998. Min Act: -0.0000

Data Index: 315657 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1314316 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1308427 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6863. Min Act: -0.0000

Data Index: 346420 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1054323 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7265. Min Act: -0.0000

Data Index: 314593 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6314. Min Act: -0.0000

Data Index: 282400 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6038. Min Act: -0.0000

Data Index: 183381 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6582. Min Act: -0.0000

Data Index: 73238 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5914. Min Act: -0.0000

Data Index: 961958 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4949. Min Act: -0.0000

Data Index: 664394 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1015340 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4805. Min Act: -0.0000

Data Index: 853676 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1182624 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.3963. Min Act: -0.0000

Data Index: 839990 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1311085 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.3739. Min Act: -0.0000

Data Index: 990806 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.3447. Min Act: -0.0000

Data Index: 461071 (C4 (Web Text))

Max Activating Token Index: 503