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

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

Neuron 1945 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: 3.5299. Min Range: -3.5299

Max Act: 3.5299. Min Act: -0.1700

Data Index: 234951 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.4566. Min Act: -0.1695

Data Index: 1401945 (Python Code)

Max Activating Token Index: 241

Text #2

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.4237. Min Act: -0.1669

Data Index: 800669 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.3992. Min Act: -0.1684

Data Index: 1062747 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.3926. Min Act: -0.1689

Data Index: 928350 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.3688. Min Act: -0.1669

Data Index: 983477 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.3109. Min Act: -0.1669

Data Index: 473497 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2972. Min Act: -0.1669

Data Index: 1513314 (Python Code)

Max Activating Token Index: 88

Text #8

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2969. Min Act: -0.1683

Data Index: 351799 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2762. Min Act: -0.1696

Data Index: 238594 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2757. Min Act: -0.1669

Data Index: 928137 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2570. Min Act: -0.1700

Data Index: 30187 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2455. Min Act: -0.1696

Data Index: 174689 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2646. Min Act: -0.1669

Data Index: 950519 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2463. Min Act: -0.1698

Data Index: 450071 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2541. Min Act: -0.1669

Data Index: 1618143 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2538. Min Act: -0.1669

Data Index: 1512914 (Python Code)

Max Activating Token Index: 46

Text #17

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2278. Min Act: -0.1669

Data Index: 1484824 (Python Code)

Max Activating Token Index: 198

Text #18

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2259. Min Act: -0.1669

Data Index: 1606065 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 3.5299. Min Range: -3.5299

Max Act: 3.2086. Min Act: -0.1669

Data Index: 1649749 (Python Code)

Max Activating Token Index: 80