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

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

Neuron 663 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: 1.6800. Min Range: -1.6800

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1193843 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2832. Min Act: 0.0000

Data Index: 513469 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1337930 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1287. Min Act: -0.0000

Data Index: 718093 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.2617. Min Act: -0.0000

Data Index: 609408 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1505. Min Act: -0.0000

Data Index: 146662 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1336. Min Act: -0.0000

Data Index: 991821 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1249. Min Act: -0.0000

Data Index: 730998 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0254. Min Act: -0.0000

Data Index: 541450 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0825. Min Act: -0.0000

Data Index: 710768 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.6800. Min Range: -1.6800

Max Act: 0.9950. Min Act: -0.0000

Data Index: 20322 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0561. Min Act: -0.0000

Data Index: 286150 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1174035 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0364. Min Act: -0.0000

Data Index: 1067458 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0310. Min Act: -0.0000

Data Index: 1226464 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1223757 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.6800. Min Range: -1.6800

Max Act: 1.0303. Min Act: -0.0000

Data Index: 909542 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.6800. Min Range: -1.6800

Max Act: 0.9938. Min Act: -0.0000

Data Index: 233182 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.6800. Min Range: -1.6800

Max Act: 0.9923. Min Act: -0.0000

Data Index: 265529 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.6800. Min Range: -1.6800

Max Act: 0.9708. Min Act: -0.0000

Data Index: 91198 (C4 (Web Text))

Max Activating Token Index: 827