Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2320 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0615. Min Range: -3.0615

Max Act: 3.0615. Min Act: -0.0000

Data Index: 1126708 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.9173. Min Act: -0.0000

Data Index: 1101256 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.8418. Min Act: -0.0001

Data Index: 685064 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.7590. Min Act: -0.0001

Data Index: 1344146 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.7094. Min Act: -0.0001

Data Index: 93899 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.8316. Min Act: -0.0000

Data Index: 524488 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5657. Min Act: -0.0000

Data Index: 1318254 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5422. Min Act: -0.0000

Data Index: 982532 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.8012. Min Act: -0.0001

Data Index: 149014 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5279. Min Act: -0.0001

Data Index: 906021 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5034. Min Act: -0.0001

Data Index: 790299 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.4757. Min Act: -0.0000

Data Index: 45020 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.8178. Min Act: -0.0000

Data Index: 416850 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5775. Min Act: -0.0001

Data Index: 706358 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5509. Min Act: -0.0001

Data Index: 1040129 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.4106. Min Act: -0.0000

Data Index: 364585 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.5196. Min Act: -0.0000

Data Index: 450856 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.2537. Min Act: -0.0001

Data Index: 496031 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.4922. Min Act: -0.0001

Data Index: 1189224 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 3.0615. Min Range: -3.0615

Max Act: 2.6219. Min Act: -0.0001

Data Index: 681084 (C4 (Web Text))

Max Activating Token Index: 284