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

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

Neuron 1574 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.2432. Min Act: -0.0001

Data Index: 1379208 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.0950. Min Act: -0.0001

Data Index: 550070 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.2089. Min Act: -0.0001

Data Index: 1386433 (Python Code)

Max Activating Token Index: 543

Text #3

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.1771. Min Act: -0.0001

Data Index: 1583548 (Python Code)

Max Activating Token Index: 535

Text #4

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.0604. Min Act: -0.0001

Data Index: 1147110 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.0290. Min Act: -0.0001

Data Index: 820861 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.0084. Min Act: -0.0001

Data Index: 1112546 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 1.2432. Min Range: -1.2432

Max Act: 1.0013. Min Act: -0.0001

Data Index: 580026 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9338. Min Act: -0.0001

Data Index: 80557 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9945. Min Act: -0.0001

Data Index: 595684 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9468. Min Act: -0.0001

Data Index: 1272218 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9808. Min Act: -0.0001

Data Index: 125543 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9680. Min Act: -0.0001

Data Index: 314374 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9902. Min Act: -0.0001

Data Index: 854199 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9575. Min Act: -0.0001

Data Index: 753702 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9910. Min Act: -0.0001

Data Index: 407077 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9422. Min Act: -0.0001

Data Index: 410095 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9338. Min Act: -0.0001

Data Index: 765891 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.9330. Min Act: -0.0001

Data Index: 955859 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.2432. Min Range: -1.2432

Max Act: 0.8702. Min Act: -0.0001

Data Index: 88804 (C4 (Web Text))

Max Activating Token Index: 768