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

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

Neuron 412 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: 4.6164. Min Range: -4.6164

Max Act: 4.6164. Min Act: -0.1700

Data Index: 1609645 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.3587. Min Act: -0.1700

Data Index: 1363723 (Python Code)

Max Activating Token Index: 509

Text #2

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.3203. Min Act: -0.1696

Data Index: 1363255 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.2493. Min Act: -0.1700

Data Index: 1418095 (Python Code)

Max Activating Token Index: 463

Text #4

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.1418. Min Act: -0.1700

Data Index: 1490832 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.1406. Min Act: -0.1700

Data Index: 1643198 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.1092. Min Act: -0.1699

Data Index: 1624610 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.1353. Min Act: -0.1700

Data Index: 1463839 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.1363. Min Act: -0.1698

Data Index: 1415222 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.1299. Min Act: -0.1700

Data Index: 1380650 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0878. Min Act: -0.1700

Data Index: 1374788 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0890. Min Act: -0.1700

Data Index: 1615390 (Python Code)

Max Activating Token Index: 756

Text #12

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0910. Min Act: -0.1691

Data Index: 1475312 (Python Code)

Max Activating Token Index: 919

Text #13

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0759. Min Act: -0.1700

Data Index: 1409393 (Python Code)

Max Activating Token Index: 880

Text #14

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0531. Min Act: -0.1699

Data Index: 1410266 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0584. Min Act: -0.1699

Data Index: 1451171 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0737. Min Act: -0.1700

Data Index: 1558872 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0624. Min Act: -0.1700

Data Index: 444272 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0404. Min Act: -0.1699

Data Index: 1360496 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 4.6164. Min Range: -4.6164

Max Act: 4.0311. Min Act: -0.1700

Data Index: 1398077 (Python Code)

Max Activating Token Index: 860