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

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

Neuron 2103 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.3099. Min Act: -0.0000

Data Index: 572944 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.2922. Min Act: -0.0001

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.3218. Min Act: -0.0001

Data Index: 883557 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.2568. Min Act: -0.0000

Data Index: 441251 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.2457. Min Act: -0.0001

Data Index: 645446 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1101954 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1778. Min Act: -0.0000

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1230377 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1499. Min Act: -0.0000

Data Index: 564530 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1514. Min Act: -0.0000

Data Index: 870657 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1638. Min Act: -0.0000

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1294697 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1971. Min Act: -0.0000

Data Index: 54765 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.2257. Min Act: -0.0001

Data Index: 185074 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.0805. Min Act: -0.0001

Data Index: 1002200 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.0800. Min Act: -0.0000

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1785. Min Act: -0.0000

Data Index: 136857 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1200274 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1064. Min Act: -0.0001

Data Index: 959160 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.3218. Min Range: -1.3218

Max Act: 1.1296. Min Act: -0.0001

Data Index: 1234973 (C4 (Web Text))

Max Activating Token Index: 833