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

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

Neuron 935 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: 3.8632. Min Range: -3.8632

Max Act: 3.8632. Min Act: -0.1700

Data Index: 103428 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.8006. Min Act: -0.1700

Data Index: 17696 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7693. Min Act: -0.1700

Data Index: 80600 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.8006. Min Act: -0.1700

Data Index: 664876 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.8006. Min Act: -0.1700

Data Index: 194283 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7693. Min Act: -0.1700

Data Index: 517698 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7693. Min Act: -0.1700

Data Index: 143661 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7693. Min Act: -0.1700

Data Index: 919590 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7067. Min Act: -0.1700

Data Index: 1251533 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7380. Min Act: -0.1700

Data Index: 319621 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7067. Min Act: -0.1700

Data Index: 1039525 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7380. Min Act: -0.1700

Data Index: 1069596 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7380. Min Act: -0.1700

Data Index: 1141950 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1195423 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7380. Min Act: -0.1700

Data Index: 138001 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7693. Min Act: -0.1700

Data Index: 406343 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7380. Min Act: -0.1700

Data Index: 286994 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.6755. Min Act: -0.1700

Data Index: 603299 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7067. Min Act: -0.1700

Data Index: 168091 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 3.8632. Min Range: -3.8632

Max Act: 3.7067. Min Act: -0.1700

Data Index: 899367 (C4 (Web Text))

Max Activating Token Index: 816