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

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

Neuron 1317 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: 5.2253. Min Range: -5.2253

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1450777 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 5.2253. Min Range: -5.2253

Max Act: 5.1883. Min Act: -0.1697

Data Index: 1531677 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 5.2253. Min Range: -5.2253

Max Act: 5.1914. Min Act: -0.1700

Data Index: 1570303 (Python Code)

Max Activating Token Index: 311

Text #3

Max Range: 5.2253. Min Range: -5.2253

Max Act: 5.0843. Min Act: -0.1700

Data Index: 1655716 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 5.2253. Min Range: -5.2253

Max Act: 5.0369. Min Act: -0.1700

Data Index: 1642724 (Python Code)

Max Activating Token Index: 976

Text #5

Max Range: 5.2253. Min Range: -5.2253

Max Act: 5.0005. Min Act: -0.1700

Data Index: 1621466 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.9633. Min Act: -0.1700

Data Index: 1570900 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.9777. Min Act: -0.1700

Data Index: 1615953 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.9762. Min Act: -0.1700

Data Index: 1426626 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.8405. Min Act: -0.1687

Data Index: 1480320 (Python Code)

Max Activating Token Index: 908

Text #10

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.7812. Min Act: -0.1700

Data Index: 1545043 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.7366. Min Act: -0.1654

Data Index: 625305 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.7741. Min Act: -0.1699

Data Index: 1465878 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.7048. Min Act: -0.1699

Data Index: 363140 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.6860. Min Act: -0.1700

Data Index: 1655510 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.6746. Min Act: -0.1699

Data Index: 1535917 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.6441. Min Act: -0.1700

Data Index: 1480955 (Python Code)

Max Activating Token Index: 741

Text #17

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.6310. Min Act: -0.1698

Data Index: 1513592 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.6403. Min Act: -0.1691

Data Index: 1533134 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 5.2253. Min Range: -5.2253

Max Act: 4.6119. Min Act: -0.1700

Data Index: 1074451 (C4 (Web Text))

Max Activating Token Index: 363