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

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

Neuron 619 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: 3.3511. Min Range: -3.3511

Max Act: 3.3511. Min Act: -0.1700

Data Index: 484920 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2814. Min Act: -0.1700

Data Index: 224677 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.3243. Min Act: -0.1700

Data Index: 1034912 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.3023. Min Act: -0.1700

Data Index: 98072 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2715. Min Act: -0.1700

Data Index: 373291 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2745. Min Act: -0.1700

Data Index: 206839 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2570. Min Act: -0.1700

Data Index: 122352 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2380. Min Act: -0.1700

Data Index: 1068613 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2210. Min Act: -0.1700

Data Index: 662469 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2393. Min Act: -0.1700

Data Index: 863946 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2227. Min Act: -0.1700

Data Index: 501919 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2186. Min Act: -0.1700

Data Index: 206078 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2074. Min Act: -0.1700

Data Index: 216705 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2077. Min Act: -0.1700

Data Index: 355264 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.2030. Min Act: -0.1700

Data Index: 349595 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.1901. Min Act: -0.1700

Data Index: 1102018 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.1842. Min Act: -0.1700

Data Index: 1137855 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.1894. Min Act: -0.1700

Data Index: 805569 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.1689. Min Act: -0.1700

Data Index: 1182585 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 3.3511. Min Range: -3.3511

Max Act: 3.1571. Min Act: -0.1700

Data Index: 1007365 (C4 (Web Text))

Max Activating Token Index: 461