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

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

Neuron 168 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: 0.7591. Min Range: -0.7591

Max Act: 0.7591. Min Act: -0.0001

Data Index: 1237615 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5896. Min Act: -0.0001

Data Index: 774446 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5426. Min Act: -0.0001

Data Index: 20640 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5697. Min Act: -0.0001

Data Index: 280007 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5935. Min Act: -0.0001

Data Index: 72663 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5206. Min Act: -0.0001

Data Index: 738180 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5232. Min Act: -0.0001

Data Index: 168902 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5295. Min Act: -0.0001

Data Index: 872675 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5088. Min Act: -0.0001

Data Index: 479396 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4901. Min Act: -0.0001

Data Index: 115087 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1031629 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4771. Min Act: -0.0001

Data Index: 41756 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4773. Min Act: -0.0001

Data Index: 65950 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4779. Min Act: -0.0001

Data Index: 1307719 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5107. Min Act: -0.0001

Data Index: 1077820 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4533. Min Act: -0.0001

Data Index: 555681 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5349. Min Act: -0.0001

Data Index: 585984 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1020932 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.4325. Min Act: -0.0001

Data Index: 1183391 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.7591. Min Range: -0.7591

Max Act: 0.5230. Min Act: -0.0001

Data Index: 717888 (C4 (Web Text))

Max Activating Token Index: 192