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

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

Neuron 954 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: 3.4997. Min Range: -3.4997

Max Act: 3.4997. Min Act: -0.1700

Data Index: 218773 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.4527. Min Act: -0.1700

Data Index: 1370339 (Python Code)

Max Activating Token Index: 222

Text #2

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3742. Min Act: -0.1700

Data Index: 818248 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3586. Min Act: -0.1700

Data Index: 42824 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3272. Min Act: -0.1700

Data Index: 261425 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3272. Min Act: -0.1700

Data Index: 1340229 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3115. Min Act: -0.1700

Data Index: 79727 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1023662 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2800. Min Act: -0.1700

Data Index: 656695 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1246017 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3272. Min Act: -0.1700

Data Index: 1246579 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2800. Min Act: -0.1700

Data Index: 1323130 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2800. Min Act: -0.1700

Data Index: 498576 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2958. Min Act: -0.1700

Data Index: 205134 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2958. Min Act: -0.1700

Data Index: 80660 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1098193 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2958. Min Act: -0.1700

Data Index: 965710 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2800. Min Act: -0.1700

Data Index: 202923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2958. Min Act: -0.1700

Data Index: 388458 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 3.4997. Min Range: -3.4997

Max Act: 3.2643. Min Act: -0.1700

Data Index: 573611 (C4 (Web Text))

Max Activating Token Index: 268