Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1668 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1397. Min Range: -5.1397

Max Act: 5.1397. Min Act: -0.1699

Data Index: 1516568 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.8116. Min Act: -0.1699

Data Index: 1419976 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.8116. Min Act: -0.1699

Data Index: 877634 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.6319. Min Act: -0.1699

Data Index: 1655734 (Python Code)

Max Activating Token Index: 311

Text #4

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.5264. Min Act: -0.1699

Data Index: 1513373 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.5342. Min Act: -0.1699

Data Index: 1539500 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.5108. Min Act: -0.1699

Data Index: 1385702 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.5381. Min Act: -0.1699

Data Index: 1549196 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.4639. Min Act: -0.1699

Data Index: 1520391 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.4952. Min Act: -0.1699

Data Index: 1424992 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.4288. Min Act: -0.1699

Data Index: 1494230 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.4444. Min Act: -0.1699

Data Index: 1394650 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3663. Min Act: -0.1699

Data Index: 1372657 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3741. Min Act: -0.1699

Data Index: 1409886 (Python Code)

Max Activating Token Index: 206

Text #14

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3936. Min Act: -0.1699

Data Index: 1374321 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3545. Min Act: -0.1699

Data Index: 1596106 (Python Code)

Max Activating Token Index: 623

Text #16

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3311. Min Act: -0.1699

Data Index: 1365251 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3155. Min Act: -0.1699

Data Index: 1400210 (Python Code)

Max Activating Token Index: 676

Text #18

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.3350. Min Act: -0.1699

Data Index: 1533311 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 5.1397. Min Range: -5.1397

Max Act: 4.2920. Min Act: -0.1699

Data Index: 1551234 (Python Code)

Max Activating Token Index: 406