Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3123 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.3647. Min Act: -0.0000

Data Index: 926654 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2692. Min Act: -0.0001

Data Index: 900610 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2582. Min Act: -0.0001

Data Index: 1146456 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2343. Min Act: -0.0000

Data Index: 957394 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1247364 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2107. Min Act: -0.0000

Data Index: 588441 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1066022 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2245. Min Act: -0.0001

Data Index: 527717 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2095. Min Act: -0.0000

Data Index: 856094 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1844. Min Act: -0.0000

Data Index: 159515 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1917. Min Act: -0.0000

Data Index: 981448 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1844. Min Act: -0.0001

Data Index: 810545 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1955. Min Act: -0.0000

Data Index: 498174 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.2035. Min Act: -0.0000

Data Index: 554804 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1882. Min Act: -0.0000

Data Index: 178045 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1255189 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1762. Min Act: -0.0001

Data Index: 450352 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1778. Min Act: -0.0000

Data Index: 760484 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1319679 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.3647. Min Range: -0.3647

Max Act: 0.1762. Min Act: -0.0000

Data Index: 56388 (C4 (Web Text))

Max Activating Token Index: 63