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

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

Neuron 485 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: 3.7139. Min Range: -3.7139

Max Act: 3.7139. Min Act: -0.1700

Data Index: 153939 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.6513. Min Act: -0.1700

Data Index: 616506 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.5260. Min Act: -0.1700

Data Index: 1280702 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4947. Min Act: -0.1700

Data Index: 751016 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4947. Min Act: -0.1700

Data Index: 723941 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.5573. Min Act: -0.1700

Data Index: 1246005 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4320. Min Act: -0.1700

Data Index: 366825 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4320. Min Act: -0.1700

Data Index: 1121471 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4947. Min Act: -0.1700

Data Index: 854251 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4320. Min Act: -0.1700

Data Index: 53054 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4947. Min Act: -0.1700

Data Index: 564858 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4320. Min Act: -0.1700

Data Index: 520425 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4320. Min Act: -0.1700

Data Index: 812557 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.4320. Min Act: -0.1700

Data Index: 16054 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.3692. Min Act: -0.1700

Data Index: 445379 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.3378. Min Act: -0.1700

Data Index: 424479 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.3692. Min Act: -0.1700

Data Index: 175884 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.2750. Min Act: -0.1700

Data Index: 688793 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.3692. Min Act: -0.1700

Data Index: 911772 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 3.7139. Min Range: -3.7139

Max Act: 3.2750. Min Act: -0.1700

Data Index: 525374 (C4 (Web Text))

Max Activating Token Index: 491