Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1653 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.6357. Min Act: -0.1700

Data Index: 1464739 (Python Code)

Max Activating Token Index: 312

Text #1

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.6211. Min Act: -0.1700

Data Index: 1606361 (Python Code)

Max Activating Token Index: 348

Text #2

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.6053. Min Act: -0.1700

Data Index: 1481272 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.5726. Min Act: -0.1700

Data Index: 1507601 (Python Code)

Max Activating Token Index: 452

Text #4

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.5726. Min Act: -0.1700

Data Index: 1397829 (Python Code)

Max Activating Token Index: 52

Text #5

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.5448. Min Act: -0.1700

Data Index: 1568533 (Python Code)

Max Activating Token Index: 519

Text #6

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.5363. Min Act: -0.1700

Data Index: 1503108 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4988. Min Act: -0.1700

Data Index: 1435094 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4816. Min Act: -0.1700

Data Index: 1576944 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.5007. Min Act: -0.1700

Data Index: 1423060 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4810. Min Act: -0.1700

Data Index: 1438157 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4856. Min Act: -0.1700

Data Index: 1556299 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4831. Min Act: -0.1700

Data Index: 1442037 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4513. Min Act: -0.1700

Data Index: 1522474 (Python Code)

Max Activating Token Index: 660

Text #14

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4957. Min Act: -0.1700

Data Index: 1386066 (Python Code)

Max Activating Token Index: 373

Text #15

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4312. Min Act: -0.1700

Data Index: 1589645 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4319. Min Act: -0.1700

Data Index: 1460263 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4405. Min Act: -0.1700

Data Index: 1376194 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4066. Min Act: -0.1700

Data Index: 1522666 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 4.6357. Min Range: -4.6357

Max Act: 4.4535. Min Act: -0.1700

Data Index: 1519326 (Python Code)

Max Activating Token Index: 197