Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 361 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.3681. Min Act: -0.1700

Data Index: 156460 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2425. Min Act: -0.1700

Data Index: 446762 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2739. Min Act: -0.1700

Data Index: 776441 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2425. Min Act: -0.1700

Data Index: 205760 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2739. Min Act: -0.1700

Data Index: 684249 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2425. Min Act: -0.1700

Data Index: 1080413 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2425. Min Act: -0.1700

Data Index: 925546 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 603008 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 1023603 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2111. Min Act: -0.1700

Data Index: 599823 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2111. Min Act: -0.1700

Data Index: 892041 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 695853 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.2111. Min Act: -0.1700

Data Index: 705164 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 817720 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 374379 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1481. Min Act: -0.1700

Data Index: 916886 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 123905 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1796. Min Act: -0.1700

Data Index: 124433 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1481. Min Act: -0.1700

Data Index: 997344 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 3.3681. Min Range: -3.3681

Max Act: 3.1166. Min Act: -0.1700

Data Index: 33660 (C4 (Web Text))

Max Activating Token Index: 423