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

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

Neuron 444 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7663. Min Act: -0.1700

Data Index: 773279 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7976. Min Act: -0.1700

Data Index: 290720 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7976. Min Act: -0.1700

Data Index: 941627 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.8132. Min Act: -0.1700

Data Index: 434413 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7350. Min Act: -0.1700

Data Index: 478094 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7976. Min Act: -0.1700

Data Index: 1234414 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7037. Min Act: -0.1700

Data Index: 1234651 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7193. Min Act: -0.1700

Data Index: 1115514 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7819. Min Act: -0.1700

Data Index: 1012098 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.8288. Min Act: -0.1700

Data Index: 725019 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6568. Min Act: -0.1700

Data Index: 1118787 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7663. Min Act: -0.1700

Data Index: 32424 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7037. Min Act: -0.1700

Data Index: 1210992 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7037. Min Act: -0.1700

Data Index: 585362 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6724. Min Act: -0.1700

Data Index: 25518 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6411. Min Act: -0.1700

Data Index: 334590 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7350. Min Act: -0.1700

Data Index: 297648 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6881. Min Act: -0.1700

Data Index: 634781 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.6411. Min Act: -0.1700

Data Index: 427515 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 3.8288. Min Range: -3.8288

Max Act: 3.7037. Min Act: -0.1700

Data Index: 766252 (C4 (Web Text))

Max Activating Token Index: 308