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

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

Neuron 128 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2995. Min Range: -3.2995

Max Act: 3.2995. Min Act: -0.0001

Data Index: 1334523 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.9927. Min Act: -0.0001

Data Index: 963965 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.9632. Min Act: -0.0001

Data Index: 1180283 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.9323. Min Act: -0.0001

Data Index: 257563 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.7744. Min Act: -0.0001

Data Index: 1223094 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.6565. Min Act: -0.0001

Data Index: 145946 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.5741. Min Act: -0.0001

Data Index: 605717 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.3651. Min Act: -0.0001

Data Index: 1227049 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.3614. Min Act: -0.0001

Data Index: 737145 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.3427. Min Act: -0.0001

Data Index: 631897 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.4586. Min Act: -0.0001

Data Index: 98659 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.3157. Min Act: -0.0001

Data Index: 339396 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.3091. Min Act: -0.0001

Data Index: 994480 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.2989. Min Act: -0.0001

Data Index: 1103100 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.3630. Min Act: -0.0001

Data Index: 620024 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.2534. Min Act: -0.0001

Data Index: 404553 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.1033. Min Act: -0.0001

Data Index: 744707 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.2151. Min Act: -0.0001

Data Index: 506108 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.2093. Min Act: -0.0001

Data Index: 1231502 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 3.2995. Min Range: -3.2995

Max Act: 2.2050. Min Act: -0.0001

Data Index: 1140605 (C4 (Web Text))

Max Activating Token Index: 16