Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7958. Min Act: -0.0000

Data Index: 929283 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1000955 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7491. Min Act: -0.0001

Data Index: 421703 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.7702. Min Act: -0.0001

Data Index: 85357 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1016449 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6540. Min Act: -0.0000

Data Index: 500610 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6398. Min Act: -0.0001

Data Index: 1109844 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6888. Min Act: -0.0000

Data Index: 46967 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6170. Min Act: -0.0001

Data Index: 689408 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5890. Min Act: -0.0000

Data Index: 122051 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6269. Min Act: -0.0000

Data Index: 873295 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1030015 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1196208 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6183. Min Act: -0.0001

Data Index: 663923 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5928. Min Act: -0.0000

Data Index: 52457 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6255. Min Act: -0.0000

Data Index: 131860 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5347. Min Act: -0.0001

Data Index: 241889 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6123. Min Act: -0.0001

Data Index: 183646 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.6349. Min Act: -0.0001

Data Index: 428933 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.7958. Min Range: -0.7958

Max Act: 0.5698. Min Act: -0.0000

Data Index: 758588 (C4 (Web Text))

Max Activating Token Index: 595