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

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

Neuron 1340 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.2667. Min Act: -0.1700

Data Index: 1264840 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.2352. Min Act: -0.1700

Data Index: 1248499 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.2038. Min Act: -0.1700

Data Index: 487698 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1566. Min Act: -0.1700

Data Index: 734480 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1880. Min Act: -0.1700

Data Index: 994643 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1566. Min Act: -0.1700

Data Index: 1021974 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1566. Min Act: -0.1700

Data Index: 771055 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1408. Min Act: -0.1700

Data Index: 1411119 (Python Code)

Max Activating Token Index: 270

Text #8

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1251. Min Act: -0.1700

Data Index: 1290702 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1251. Min Act: -0.1700

Data Index: 762396 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1093. Min Act: -0.1700

Data Index: 1252020 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1251. Min Act: -0.1700

Data Index: 184065 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1251. Min Act: -0.1700

Data Index: 980966 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1251. Min Act: -0.1700

Data Index: 322894 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.0935. Min Act: -0.1700

Data Index: 982446 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.0935. Min Act: -0.1700

Data Index: 120410 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.0935. Min Act: -0.1700

Data Index: 803730 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.1093. Min Act: -0.1700

Data Index: 1225246 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.0935. Min Act: -0.1700

Data Index: 1253930 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 3.2667. Min Range: -3.2667

Max Act: 3.0935. Min Act: -0.1700

Data Index: 985109 (C4 (Web Text))

Max Activating Token Index: 850