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

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

Neuron 1230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.4225. Min Act: -0.1700

Data Index: 250239 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.3600. Min Act: -0.1700

Data Index: 274770 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.3912. Min Act: -0.1700

Data Index: 1347178 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.3600. Min Act: -0.1700

Data Index: 892795 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2662. Min Act: -0.1700

Data Index: 402995 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2662. Min Act: -0.1700

Data Index: 220983 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2662. Min Act: -0.1700

Data Index: 897171 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2037. Min Act: -0.1700

Data Index: 613228 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2350. Min Act: -0.1700

Data Index: 399341 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2037. Min Act: -0.1700

Data Index: 362430 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.2037. Min Act: -0.1700

Data Index: 756603 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.1725. Min Act: -0.1700

Data Index: 355546 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.1412. Min Act: -0.1700

Data Index: 1128397 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.1725. Min Act: -0.1700

Data Index: 556073 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.1725. Min Act: -0.1700

Data Index: 1189564 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.1100. Min Act: -0.1700

Data Index: 1239496 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.0787. Min Act: -0.1700

Data Index: 507422 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.1412. Min Act: -0.1700

Data Index: 1054546 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.0475. Min Act: -0.1700

Data Index: 617331 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 5.4225. Min Range: -5.4225

Max Act: 5.0475. Min Act: -0.1700

Data Index: 208291 (C4 (Web Text))

Max Activating Token Index: 507