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

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

Neuron 1010 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: 2.7706. Min Range: -2.7706

Max Act: 2.7706. Min Act: -0.1698

Data Index: 1517157 (Python Code)

Max Activating Token Index: 752

Text #1

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.7470. Min Act: -0.1700

Data Index: 467906 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.7689. Min Act: -0.1696

Data Index: 1596040 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.7411. Min Act: -0.1700

Data Index: 987554 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.7421. Min Act: -0.1699

Data Index: 720990 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.6642. Min Act: -0.1699

Data Index: 1495905 (Python Code)

Max Activating Token Index: 69

Text #6

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.6577. Min Act: -0.1700

Data Index: 540866 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.6420. Min Act: -0.1698

Data Index: 1595214 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.6026. Min Act: -0.1694

Data Index: 1192944 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.6184. Min Act: -0.1698

Data Index: 1387758 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5719. Min Act: -0.1700

Data Index: 770705 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5629. Min Act: -0.1699

Data Index: 1379889 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5686. Min Act: -0.1689

Data Index: 1626144 (Python Code)

Max Activating Token Index: 929

Text #13

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5531. Min Act: -0.1700

Data Index: 449291 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5392. Min Act: -0.1700

Data Index: 1448963 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5376. Min Act: -0.1694

Data Index: 1647231 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5447. Min Act: -0.1700

Data Index: 1557221 (Python Code)

Max Activating Token Index: 638

Text #17

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5596. Min Act: -0.1699

Data Index: 1594472 (Python Code)

Max Activating Token Index: 927

Text #18

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5375. Min Act: -0.1700

Data Index: 1328031 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.7706. Min Range: -2.7706

Max Act: 2.5292. Min Act: -0.1700

Data Index: 1330631 (C4 (Web Text))

Max Activating Token Index: 691