Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1776 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.2101. Min Act: -0.1700

Data Index: 70617 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.2258. Min Act: -0.1700

Data Index: 1240666 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1943. Min Act: -0.1700

Data Index: 658853 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1786. Min Act: -0.1700

Data Index: 497489 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1156. Min Act: -0.1700

Data Index: 433620 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1112671 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1471. Min Act: -0.1700

Data Index: 851590 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1288335 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1185195 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1094873 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0683. Min Act: -0.1700

Data Index: 680759 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0998. Min Act: -0.1700

Data Index: 286435 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0998. Min Act: -0.1700

Data Index: 1326379 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0525. Min Act: -0.1700

Data Index: 907135 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1225858 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0683. Min Act: -0.1700

Data Index: 744017 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0841. Min Act: -0.1700

Data Index: 676253 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0683. Min Act: -0.1700

Data Index: 466338 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0525. Min Act: -0.1700

Data Index: 870856 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 3.2258. Min Range: -3.2258

Max Act: 3.0367. Min Act: -0.1700

Data Index: 406453 (C4 (Web Text))

Max Activating Token Index: 132