Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2505 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5370. Min Range: -3.5370

Max Act: 3.5370. Min Act: -0.0000

Data Index: 465328 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.5370. Min Range: -3.5370

Max Act: 3.4907. Min Act: -0.0000

Data Index: 887547 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.5165. Min Act: -0.0000

Data Index: 277403 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.7492. Min Act: -0.0000

Data Index: 878860 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.8706. Min Act: -0.0000

Data Index: 923934 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.7436. Min Act: -0.0000

Data Index: 245564 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.7199. Min Act: -0.0000

Data Index: 1166748 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.6296. Min Act: -0.0000

Data Index: 804080 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.2985. Min Act: -0.0000

Data Index: 272194 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.5985. Min Act: -0.0000

Data Index: 722070 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.3151. Min Act: -0.0000

Data Index: 469827 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.3587. Min Act: -0.0000

Data Index: 1264595 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.0833. Min Act: -0.0000

Data Index: 4102 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.1504. Min Act: -0.0000

Data Index: 714870 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.0461. Min Act: -0.0000

Data Index: 921937 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 3.5370. Min Range: -3.5370

Max Act: 1.9213. Min Act: -0.0000

Data Index: 208007 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 3.5370. Min Range: -3.5370

Max Act: 1.8191. Min Act: -0.0000

Data Index: 27604 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.0277. Min Act: -0.0000

Data Index: 627153 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.0953. Min Act: -0.0000

Data Index: 852705 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 3.5370. Min Range: -3.5370

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1136068 (C4 (Web Text))

Max Activating Token Index: 728