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

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

Neuron 4029 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.4122. Min Act: -0.0001

Data Index: 399570 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2273. Min Act: -0.0001

Data Index: 916809 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2273. Min Act: -0.0001

Data Index: 877233 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2273. Min Act: -0.0001

Data Index: 328151 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2273. Min Act: -0.0001

Data Index: 654051 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.2273. Min Act: -0.0001

Data Index: 829220 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0377. Min Act: -0.0001

Data Index: 881351 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0197. Min Act: -0.0001

Data Index: 980796 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.9714. Min Act: -0.0001

Data Index: 411900 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.9858. Min Act: -0.0001

Data Index: 45409 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.9129. Min Act: -0.0001

Data Index: 1205039 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.8983. Min Act: -0.0001

Data Index: 360716 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.4122. Min Range: -1.4122

Max Act: 1.0453. Min Act: -0.0001

Data Index: 1419646 (Python Code)

Max Activating Token Index: 923

Text #13

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.7910. Min Act: -0.0001

Data Index: 446018 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.9534. Min Act: -0.0001

Data Index: 889518 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.8550. Min Act: -0.0001

Data Index: 49292 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.8640. Min Act: -0.0001

Data Index: 1333193 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.8845. Min Act: -0.0001

Data Index: 1253149 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.8786. Min Act: -0.0001

Data Index: 297126 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.4122. Min Range: -1.4122

Max Act: 0.8733. Min Act: -0.0001

Data Index: 604122 (C4 (Web Text))

Max Activating Token Index: 215