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

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

Neuron 3308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9492. Min Range: -2.9492

Max Act: 2.9492. Min Act: -0.0000

Data Index: 759227 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 2.9492. Min Range: -2.9492

Max Act: 2.1349. Min Act: -0.0000

Data Index: 571536 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 2.9492. Min Range: -2.9492

Max Act: 2.1955. Min Act: -0.0000

Data Index: 1107563 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.9492. Min Range: -2.9492

Max Act: 2.1081. Min Act: -0.0000

Data Index: 846961 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1305412 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.8176. Min Act: -0.0000

Data Index: 120257 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.6686. Min Act: -0.0001

Data Index: 391273 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7505. Min Act: -0.0000

Data Index: 763652 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.8450. Min Act: -0.0000

Data Index: 508822 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7491. Min Act: -0.0000

Data Index: 554428 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7386. Min Act: -0.0000

Data Index: 992554 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7342. Min Act: -0.0000

Data Index: 376863 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7341. Min Act: -0.0000

Data Index: 168813 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1340680 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.6856. Min Act: -0.0000

Data Index: 58388 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.6727. Min Act: -0.0000

Data Index: 600610 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.6479. Min Act: -0.0000

Data Index: 242789 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.5557. Min Act: -0.0000

Data Index: 53008 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.6335. Min Act: -0.0000

Data Index: 525386 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 2.9492. Min Range: -2.9492

Max Act: 1.7136. Min Act: -0.0001

Data Index: 758230 (C4 (Web Text))

Max Activating Token Index: 858