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

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

Neuron 919 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: 3.2315. Min Range: -3.2315

Max Act: 3.2315. Min Act: -0.1700

Data Index: 277288 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1686. Min Act: -0.1700

Data Index: 584684 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1528. Min Act: -0.1700

Data Index: 153883 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1213. Min Act: -0.1700

Data Index: 566094 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1213. Min Act: -0.1700

Data Index: 649511 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1686. Min Act: -0.1700

Data Index: 465727 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1056. Min Act: -0.1700

Data Index: 1356529 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.1056. Min Act: -0.1700

Data Index: 435138 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0898. Min Act: -0.1700

Data Index: 156584 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0740. Min Act: -0.1700

Data Index: 1090083 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0740. Min Act: -0.1700

Data Index: 775526 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0740. Min Act: -0.1700

Data Index: 182521 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0425. Min Act: -0.1700

Data Index: 475466 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0583. Min Act: -0.1700

Data Index: 710324 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0425. Min Act: -0.1700

Data Index: 340224 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0109. Min Act: -0.1700

Data Index: 781671 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0267. Min Act: -0.1700

Data Index: 266678 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 3.2315. Min Range: -3.2315

Max Act: 2.9951. Min Act: -0.1700

Data Index: 1036372 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0267. Min Act: -0.1700

Data Index: 888402 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 3.2315. Min Range: -3.2315

Max Act: 3.0109. Min Act: -0.1700

Data Index: 859006 (C4 (Web Text))

Max Activating Token Index: 466