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

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

Neuron 1418 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.2436. Min Act: -0.1700

Data Index: 1174259 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.1499. Min Act: -0.1700

Data Index: 312356 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.1186. Min Act: -0.1700

Data Index: 835845 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.0249. Min Act: -0.1700

Data Index: 897644 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.0249. Min Act: -0.1700

Data Index: 21254 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.0561. Min Act: -0.1700

Data Index: 860546 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.0249. Min Act: -0.1700

Data Index: 1026411 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 5.2436. Min Range: -5.2436

Max Act: 5.0249. Min Act: -0.1700

Data Index: 106723 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.9624. Min Act: -0.1700

Data Index: 1162777 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.9936. Min Act: -0.1700

Data Index: 546976 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.9311. Min Act: -0.1700

Data Index: 1105816 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.9311. Min Act: -0.1700

Data Index: 142142 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8999. Min Act: -0.1700

Data Index: 1350879 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8686. Min Act: -0.1700

Data Index: 396974 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.9624. Min Act: -0.1700

Data Index: 783466 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8686. Min Act: -0.1700

Data Index: 1182886 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8686. Min Act: -0.1700

Data Index: 1310656 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8686. Min Act: -0.1700

Data Index: 1340502 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8686. Min Act: -0.1700

Data Index: 373159 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 5.2436. Min Range: -5.2436

Max Act: 4.8374. Min Act: -0.1700

Data Index: 703222 (C4 (Web Text))

Max Activating Token Index: 722