Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2160 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3532. Min Act: -0.0001

Data Index: 986379 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3035. Min Act: -0.0001

Data Index: 325426 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3021. Min Act: -0.0001

Data Index: 752272 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.3000. Min Act: -0.0001

Data Index: 761277 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2865. Min Act: -0.0001

Data Index: 940050 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2705. Min Act: -0.0001

Data Index: 324145 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2511. Min Act: -0.0001

Data Index: 707115 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2565. Min Act: -0.0001

Data Index: 377088 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2365. Min Act: -0.0001

Data Index: 110004 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2434. Min Act: -0.0001

Data Index: 20728 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2390. Min Act: -0.0001

Data Index: 801197 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2322. Min Act: -0.0001

Data Index: 469542 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2289. Min Act: -0.0001

Data Index: 481354 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2393. Min Act: -0.0001

Data Index: 480319 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2408. Min Act: -0.0001

Data Index: 912265 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2182. Min Act: -0.0001

Data Index: 390748 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2299. Min Act: -0.0001

Data Index: 875693 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2223. Min Act: -0.0001

Data Index: 149526 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2435. Min Act: -0.0001

Data Index: 1050701 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.3532. Min Range: -0.3532

Max Act: 0.2109. Min Act: -0.0001

Data Index: 704580 (C4 (Web Text))

Max Activating Token Index: 459