Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1489 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.6674. Min Act: -0.0003

Data Index: 463953 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5031. Min Act: -0.0003

Data Index: 1171484 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4980. Min Act: -0.0003

Data Index: 666408 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.6006. Min Act: -0.0003

Data Index: 1296365 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3363. Min Act: -0.0003

Data Index: 738999 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3138. Min Act: -0.0003

Data Index: 43813 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.6670. Min Act: -0.0003

Data Index: 1355680 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.2791. Min Act: -0.0003

Data Index: 1223934 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5635. Min Act: -0.0003

Data Index: 1338062 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.5215. Min Act: -0.0003

Data Index: 1137972 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.2029. Min Act: -0.0003

Data Index: 1197878 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.1919. Min Act: -0.0003

Data Index: 641723 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3053. Min Act: -0.0003

Data Index: 272437 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3784. Min Act: -0.0003

Data Index: 939089 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.4172. Min Act: -0.0003

Data Index: 134104 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.1711. Min Act: -0.0003

Data Index: 293222 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3276. Min Act: -0.0003

Data Index: 1052512 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3171. Min Act: -0.0003

Data Index: 355888 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.3281. Min Act: -0.0003

Data Index: 354431 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 1.6674. Min Range: -1.6674

Max Act: 1.2131. Min Act: -0.0003

Data Index: 978577 (C4 (Web Text))

Max Activating Token Index: 439