Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3540 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5514. Min Act: -0.0002

Data Index: 240479 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5146. Min Act: -0.0001

Data Index: 797828 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5284. Min Act: -0.0001

Data Index: 1042551 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4610. Min Act: -0.0001

Data Index: 962169 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4641. Min Act: -0.0001

Data Index: 86232 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5121. Min Act: -0.0002

Data Index: 840490 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4641. Min Act: -0.0001

Data Index: 640391 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4291. Min Act: -0.0002

Data Index: 1010747 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4697. Min Act: -0.0002

Data Index: 785759 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4360. Min Act: -0.0001

Data Index: 850520 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4544. Min Act: -0.0002

Data Index: 262083 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4434. Min Act: -0.0002

Data Index: 1181254 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.3931. Min Act: -0.0001

Data Index: 455907 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.3481. Min Act: -0.0001

Data Index: 223574 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4259. Min Act: -0.0001

Data Index: 955694 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4361. Min Act: -0.0001

Data Index: 208174 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4481. Min Act: -0.0001

Data Index: 272724 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.3948. Min Act: -0.0001

Data Index: 263510 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4254. Min Act: -0.0001

Data Index: 14937 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4246. Min Act: -0.0002

Data Index: 1345800 (C4 (Web Text))

Max Activating Token Index: 488