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

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

Neuron 1770 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: 3.4239. Min Range: -3.4239

Max Act: 3.4239. Min Act: -0.0000

Data Index: 852618 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 3.4239. Min Range: -3.4239

Max Act: 3.1424. Min Act: -0.0000

Data Index: 123898 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 3.4239. Min Range: -3.4239

Max Act: 3.2553. Min Act: -0.0000

Data Index: 619921 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.9290. Min Act: -0.0000

Data Index: 1064471 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.4239. Min Range: -3.4239

Max Act: 3.1649. Min Act: -0.0000

Data Index: 1154841 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 3.4239. Min Range: -3.4239

Max Act: 3.1277. Min Act: -0.0000

Data Index: 740325 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.8440. Min Act: -0.0000

Data Index: 1042931 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 3.4239. Min Range: -3.4239

Max Act: 3.0503. Min Act: -0.0000

Data Index: 82671 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 3.4239. Min Range: -3.4239

Max Act: 3.0134. Min Act: -0.0000

Data Index: 61910 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.8572. Min Act: -0.0001

Data Index: 35941 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.9794. Min Act: -0.0000

Data Index: 531256 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.9287. Min Act: -0.0000

Data Index: 810944 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.9331. Min Act: -0.0000

Data Index: 1021526 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.8790. Min Act: -0.0000

Data Index: 102908 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.8355. Min Act: -0.0001

Data Index: 99105 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.8820. Min Act: -0.0000

Data Index: 374803 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.7738. Min Act: -0.0000

Data Index: 668383 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.7620. Min Act: -0.0000

Data Index: 1297937 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.5480. Min Act: -0.0000

Data Index: 521863 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 3.4239. Min Range: -3.4239

Max Act: 2.5581. Min Act: -0.0000

Data Index: 211917 (C4 (Web Text))

Max Activating Token Index: 456