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

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

Neuron 3612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2087. Min Range: -3.2087

Max Act: 3.2087. Min Act: -0.0000

Data Index: 42154 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 3.2087. Min Range: -3.2087

Max Act: 3.1241. Min Act: -0.0000

Data Index: 1071078 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 3.2087. Min Range: -3.2087

Max Act: 3.0676. Min Act: -0.0000

Data Index: 410136 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.8160. Min Act: -0.0000

Data Index: 157177 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.8324. Min Act: -0.0000

Data Index: 1279874 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.7464. Min Act: -0.0000

Data Index: 1130739 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.7160. Min Act: -0.0000

Data Index: 758103 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.7031. Min Act: -0.0000

Data Index: 453384 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.4019. Min Act: -0.0000

Data Index: 34545 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.6439. Min Act: -0.0000

Data Index: 789442 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.4856. Min Act: -0.0000

Data Index: 1354028 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.4438. Min Act: -0.0000

Data Index: 114933 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.3966. Min Act: -0.0000

Data Index: 986179 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.5199. Min Act: -0.0000

Data Index: 600660 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.4973. Min Act: -0.0000

Data Index: 51986 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.3716. Min Act: -0.0000

Data Index: 51161 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.3537. Min Act: -0.0000

Data Index: 1064772 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.3356. Min Act: -0.0000

Data Index: 953179 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.3216. Min Act: -0.0000

Data Index: 36203 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 3.2087. Min Range: -3.2087

Max Act: 2.2955. Min Act: -0.0000

Data Index: 400342 (C4 (Web Text))

Max Activating Token Index: 11