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

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

Neuron 259 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2214. Min Act: -0.0001

Data Index: 961964 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1117241 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.2516. Min Act: -0.0001

Data Index: 585757 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1995. Min Act: -0.0001

Data Index: 980400 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1832. Min Act: -0.0001

Data Index: 662481 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1416. Min Act: -0.0001

Data Index: 739198 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1572. Min Act: -0.0001

Data Index: 947854 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1318. Min Act: -0.0001

Data Index: 622479 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1458. Min Act: -0.0001

Data Index: 1374742 (Python Code)

Max Activating Token Index: 265

Text #9

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1557. Min Act: -0.0001

Data Index: 367457 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1552. Min Act: -0.0001

Data Index: 399000 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1598987 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1492. Min Act: -0.0001

Data Index: 824077 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1486. Min Act: -0.0001

Data Index: 5047 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1309. Min Act: -0.0001

Data Index: 308358 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1290. Min Act: -0.0001

Data Index: 718106 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1106. Min Act: -0.0001

Data Index: 899802 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1369. Min Act: -0.0001

Data Index: 333357 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1258. Min Act: -0.0001

Data Index: 607336 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.2516. Min Range: -0.2516

Max Act: 0.1301. Min Act: -0.0001

Data Index: 230973 (C4 (Web Text))

Max Activating Token Index: 967