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

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

Neuron 3112 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.8370. Min Act: -0.0000

Data Index: 228262 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.4331. Min Act: -0.0000

Data Index: 1098286 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.3968. Min Act: -0.0000

Data Index: 380749 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.0939. Min Act: -0.0000

Data Index: 770433 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.0926. Min Act: -0.0000

Data Index: 529545 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.9487. Min Act: -0.0000

Data Index: 666006 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.0372. Min Act: -0.0000

Data Index: 881133 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.0334. Min Act: -0.0000

Data Index: 974087 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.1242. Min Act: -0.0000

Data Index: 711144 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 2.8370. Min Range: -2.8370

Max Act: 2.0548. Min Act: -0.0000

Data Index: 1093739 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.8734. Min Act: -0.0000

Data Index: 140817 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.7360. Min Act: -0.0000

Data Index: 1295062 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.6849. Min Act: -0.0000

Data Index: 325159 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.8962. Min Act: -0.0000

Data Index: 502222 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.7789. Min Act: -0.0000

Data Index: 349104 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.7385. Min Act: -0.0000

Data Index: 1036565 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.7369. Min Act: -0.0000

Data Index: 1302026 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.7004. Min Act: -0.0000

Data Index: 343821 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.5811. Min Act: -0.0000

Data Index: 494676 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 2.8370. Min Range: -2.8370

Max Act: 1.5266. Min Act: -0.0000

Data Index: 204718 (C4 (Web Text))

Max Activating Token Index: 432