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

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

Neuron 5775 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0329. Min Range: -4.0329

Max Act: 4.0329. Min Act: 0.0000

Data Index: 876754 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 4.0329. Min Range: -4.0329

Max Act: 3.6461. Min Act: -0.0000

Data Index: 394765 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 4.0329. Min Range: -4.0329

Max Act: 3.5006. Min Act: -0.0000

Data Index: 1045548 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 4.0329. Min Range: -4.0329

Max Act: 3.0671. Min Act: -0.0000

Data Index: 242467 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.9743. Min Act: -0.0000

Data Index: 1172957 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.9573. Min Act: -0.0000

Data Index: 169859 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.9334. Min Act: -0.0000

Data Index: 814090 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.7918. Min Act: -0.0000

Data Index: 816060 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 4.0329. Min Range: -4.0329

Max Act: 3.0219. Min Act: -0.0000

Data Index: 1188695 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.6971. Min Act: 0.0001

Data Index: 1162359 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.8483. Min Act: -0.0000

Data Index: 6393 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.8116. Min Act: 0.0000

Data Index: 141841 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.6656. Min Act: 0.0000

Data Index: 508221 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.5893. Min Act: -0.0000

Data Index: 290098 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.6680. Min Act: -0.0000

Data Index: 663454 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.5295. Min Act: 0.0000

Data Index: 67396 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.6488. Min Act: -0.0000

Data Index: 381052 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.4936. Min Act: -0.0000

Data Index: 259494 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.6228. Min Act: -0.0000

Data Index: 156941 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 4.0329. Min Range: -4.0329

Max Act: 2.7629. Min Act: -0.0000

Data Index: 52874 (C4 (Web Text))

Max Activating Token Index: 42