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

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

Neuron 642 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: 3.1386. Min Range: -3.1386

Max Act: 3.1386. Min Act: -0.1700

Data Index: 1109995 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.1228. Min Act: -0.1700

Data Index: 504055 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.1070. Min Act: -0.1700

Data Index: 598137 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.1228. Min Act: -0.1700

Data Index: 149101 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0755. Min Act: -0.1700

Data Index: 789988 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0597. Min Act: -0.1700

Data Index: 651215 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0755. Min Act: -0.1700

Data Index: 201208 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0755. Min Act: -0.1700

Data Index: 259453 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0439. Min Act: -0.1700

Data Index: 647942 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0439. Min Act: -0.1700

Data Index: 892663 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0597. Min Act: -0.1700

Data Index: 805857 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0597. Min Act: -0.1700

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0439. Min Act: -0.1700

Data Index: 573755 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0281. Min Act: -0.1700

Data Index: 210867 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0123. Min Act: -0.1700

Data Index: 433281 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0123. Min Act: -0.1700

Data Index: 264235 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0281. Min Act: -0.1700

Data Index: 460885 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0123. Min Act: -0.1700

Data Index: 1089091 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0281. Min Act: -0.1700

Data Index: 250424 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 3.1386. Min Range: -3.1386

Max Act: 3.0123. Min Act: -0.1700

Data Index: 1081892 (C4 (Web Text))

Max Activating Token Index: 15