Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.2091. Min Act: -0.0000

Data Index: 951752 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1778. Min Act: -0.0001

Data Index: 196062 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1751. Min Act: -0.0001

Data Index: 200636 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1631150 (Python Code)

Max Activating Token Index: 442

Text #4

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1405. Min Act: -0.0001

Data Index: 896972 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1405. Min Act: -0.0000

Data Index: 525212 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1390. Min Act: -0.0001

Data Index: 332971 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1317. Min Act: -0.0000

Data Index: 283369 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1351. Min Act: -0.0000

Data Index: 224213 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1381. Min Act: -0.0001

Data Index: 472339 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1373. Min Act: -0.0001

Data Index: 864130 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1286. Min Act: -0.0001

Data Index: 1642276 (Python Code)

Max Activating Token Index: 665

Text #12

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1339. Min Act: -0.0001

Data Index: 336782 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1382. Min Act: -0.0001

Data Index: 316025 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1245. Min Act: -0.0000

Data Index: 221406 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1312. Min Act: -0.0000

Data Index: 766424 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1276479 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1286987 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1144. Min Act: -0.0001

Data Index: 159865 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.2091. Min Range: -0.2091

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1648396 (Python Code)

Max Activating Token Index: 226