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

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

Neuron 660 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5356. Min Act: -0.1700

Data Index: 710089 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5356. Min Act: -0.1700

Data Index: 149799 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5356. Min Act: -0.1700

Data Index: 9879 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5042. Min Act: -0.1700

Data Index: 907389 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5042. Min Act: -0.1700

Data Index: 412532 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5042. Min Act: -0.1700

Data Index: 1254278 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.5042. Min Act: -0.1700

Data Index: 98714 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4415. Min Act: -0.1700

Data Index: 269338 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4415. Min Act: -0.1700

Data Index: 710443 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4415. Min Act: -0.1700

Data Index: 778143 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4415. Min Act: -0.1700

Data Index: 788854 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4102. Min Act: -0.1700

Data Index: 431466 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4102. Min Act: -0.1700

Data Index: 1211400 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4102. Min Act: -0.1700

Data Index: 211621 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4102. Min Act: -0.1700

Data Index: 925385 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4102. Min Act: -0.1700

Data Index: 174640 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.3788. Min Act: -0.1700

Data Index: 374101 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.4102. Min Act: -0.1700

Data Index: 226899 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.3474. Min Act: -0.1700

Data Index: 55131 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 3.5356. Min Range: -3.5356

Max Act: 3.3788. Min Act: -0.1700

Data Index: 418153 (C4 (Web Text))

Max Activating Token Index: 869