Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1496 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.9571. Min Act: -0.1700

Data Index: 808962 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.9571. Min Act: -0.1700

Data Index: 580145 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.9571. Min Act: -0.1700

Data Index: 1333407 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.9884. Min Act: -0.1700

Data Index: 490882 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8634. Min Act: -0.1700

Data Index: 709079 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8946. Min Act: -0.1700

Data Index: 1043394 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8946. Min Act: -0.1700

Data Index: 369905 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8634. Min Act: -0.1700

Data Index: 1103615 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8321. Min Act: -0.1700

Data Index: 1105804 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.7696. Min Act: -0.1700

Data Index: 1345080 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8321. Min Act: -0.1700

Data Index: 374955 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8321. Min Act: -0.1700

Data Index: 519363 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.7696. Min Act: -0.1700

Data Index: 731190 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.7696. Min Act: -0.1700

Data Index: 218434 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8946. Min Act: -0.1700

Data Index: 1325189 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.7696. Min Act: -0.1700

Data Index: 839480 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.8009. Min Act: -0.1700

Data Index: 887284 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.7384. Min Act: -0.1700

Data Index: 362980 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.7696. Min Act: -0.1700

Data Index: 5932 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 5.9884. Min Range: -5.9884

Max Act: 5.6759. Min Act: -0.1700

Data Index: 333687 (C4 (Web Text))

Max Activating Token Index: 272