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

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

Neuron 1083 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: 4.7947. Min Range: -4.7947

Max Act: 4.7947. Min Act: -0.1700

Data Index: 1378207 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.6439. Min Act: -0.1695

Data Index: 1449388 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.5910. Min Act: -0.1700

Data Index: 942318 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.5275. Min Act: -0.1672

Data Index: 1579283 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.3763. Min Act: -0.1700

Data Index: 1648589 (Python Code)

Max Activating Token Index: 957

Text #5

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.3405. Min Act: -0.1699

Data Index: 1474358 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.2802. Min Act: -0.1699

Data Index: 1484530 (Python Code)

Max Activating Token Index: 872

Text #7

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.2714. Min Act: -0.1699

Data Index: 1507540 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.2512. Min Act: -0.1700

Data Index: 830015 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.2521. Min Act: -0.1700

Data Index: 1570243 (Python Code)

Max Activating Token Index: 972

Text #10

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.2003. Min Act: -0.1700

Data Index: 1596923 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.1593. Min Act: -0.1700

Data Index: 1588909 (Python Code)

Max Activating Token Index: 119

Text #12

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.1685. Min Act: -0.1699

Data Index: 1493605 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.1525. Min Act: -0.1699

Data Index: 1601187 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.1013. Min Act: -0.1697

Data Index: 1375527 (Python Code)

Max Activating Token Index: 391

Text #15

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.0681. Min Act: -0.1698

Data Index: 711660 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.0720. Min Act: -0.1700

Data Index: 235389 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.0658. Min Act: -0.1679

Data Index: 1041381 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.0229. Min Act: -0.1700

Data Index: 118428 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 4.7947. Min Range: -4.7947

Max Act: 4.0221. Min Act: -0.1700

Data Index: 1484917 (Python Code)

Max Activating Token Index: 299