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

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

Neuron 4586 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5497. Min Act: -0.0000

Data Index: 960853 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4977. Min Act: -0.0000

Data Index: 754474 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5020. Min Act: -0.0000

Data Index: 158887 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1226358 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4521. Min Act: 0.0000

Data Index: 732077 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4657. Min Act: -0.0000

Data Index: 222802 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4559. Min Act: -0.0000

Data Index: 224046 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4467. Min Act: -0.0000

Data Index: 358670 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4372. Min Act: -0.0000

Data Index: 645443 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1019327 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4448. Min Act: -0.0000

Data Index: 682773 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1208931 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4499. Min Act: -0.0000

Data Index: 253057 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4371. Min Act: -0.0000

Data Index: 982278 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4374. Min Act: -0.0000

Data Index: 943841 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1224082 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4522. Min Act: -0.0000

Data Index: 345912 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4580. Min Act: -0.0000

Data Index: 934236 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1174379 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4246. Min Act: -0.0000

Data Index: 810913 (C4 (Web Text))

Max Activating Token Index: 139