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

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

Neuron 360 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0149. Min Range: -3.0149

Max Act: 3.0149. Min Act: -0.0001

Data Index: 1107037 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.4352. Min Act: -0.0001

Data Index: 1011588 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.3619. Min Act: -0.0001

Data Index: 816743 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.3106. Min Act: -0.0001

Data Index: 1181829 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.4276. Min Act: -0.0001

Data Index: 1518395 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.2476. Min Act: -0.0001

Data Index: 1186181 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.1046. Min Act: -0.0001

Data Index: 1626479 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.1769. Min Act: -0.0001

Data Index: 1389994 (Python Code)

Max Activating Token Index: 294

Text #8

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.1094. Min Act: -0.0001

Data Index: 45090 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.0425. Min Act: -0.0001

Data Index: 81267 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.1818. Min Act: -0.0001

Data Index: 1153201 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.9785. Min Act: -0.0001

Data Index: 1429866 (Python Code)

Max Activating Token Index: 139

Text #12

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.9306. Min Act: -0.0001

Data Index: 1615365 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.1634. Min Act: -0.0001

Data Index: 40398 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.9905. Min Act: -0.0001

Data Index: 310911 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.0149. Min Range: -3.0149

Max Act: 1.0044. Min Act: -0.0001

Data Index: 1638703 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1476537 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.8747. Min Act: -0.0001

Data Index: 1577349 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.9304. Min Act: -0.0001

Data Index: 1500726 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 3.0149. Min Range: -3.0149

Max Act: 0.8996. Min Act: -0.0001

Data Index: 199905 (C4 (Web Text))

Max Activating Token Index: 980