Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1160 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3124. Min Act: -0.0003

Data Index: 1189468 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3091. Min Act: -0.0003

Data Index: 1146380 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3393. Min Act: -0.0003

Data Index: 30412 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.3156. Min Act: -0.0003

Data Index: 1180386 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2768. Min Act: -0.0003

Data Index: 1032108 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2894. Min Act: -0.0003

Data Index: 652707 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2727. Min Act: -0.0003

Data Index: 414166 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2944. Min Act: -0.0003

Data Index: 366860 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2722. Min Act: -0.0003

Data Index: 449351 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2879. Min Act: -0.0003

Data Index: 1217617 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2873. Min Act: -0.0003

Data Index: 1336918 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2681. Min Act: -0.0003

Data Index: 417934 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2600. Min Act: -0.0003

Data Index: 599354 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2547. Min Act: -0.0003

Data Index: 1050654 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2578. Min Act: -0.0003

Data Index: 617164 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2768. Min Act: -0.0003

Data Index: 878812 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2644. Min Act: -0.0003

Data Index: 729594 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2541. Min Act: -0.0003

Data Index: 1302560 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2465. Min Act: -0.0003

Data Index: 5450 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.3393. Min Range: -0.3393

Max Act: 0.2541. Min Act: -0.0003

Data Index: 409211 (C4 (Web Text))

Max Activating Token Index: 293