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

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

Neuron 5125 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.2460. Min Act: -0.0000

Data Index: 93575 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.2347. Min Act: -0.0000

Data Index: 233186 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.2371. Min Act: -0.0000

Data Index: 1182982 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.1423. Min Act: -0.0000

Data Index: 713160 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.9265. Min Act: -0.0000

Data Index: 267576 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.0977. Min Act: -0.0001

Data Index: 1147257 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.0411. Min Act: -0.0000

Data Index: 446006 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.0655. Min Act: -0.0001

Data Index: 613936 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.9600. Min Act: -0.0001

Data Index: 1014646 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.8312. Min Act: -0.0001

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7416. Min Act: -0.0000

Data Index: 583812 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 2.2460. Min Range: -2.2460

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1273900 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.9029. Min Act: -0.0000

Data Index: 1351070 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7300. Min Act: -0.0000

Data Index: 558450 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.8144. Min Act: -0.0000

Data Index: 222131 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7290. Min Act: -0.0000

Data Index: 779955 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7116. Min Act: -0.0000

Data Index: 891223 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.8324. Min Act: -0.0000

Data Index: 45070 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.9789. Min Act: -0.0000

Data Index: 1233509 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 2.2460. Min Range: -2.2460

Max Act: 1.7164. Min Act: -0.0000

Data Index: 254338 (C4 (Web Text))

Max Activating Token Index: 879