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

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

Neuron 1856 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: 5.6479. Min Range: -5.6479

Max Act: 5.6479. Min Act: -0.1700

Data Index: 947441 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.5541. Min Act: -0.1699

Data Index: 262099 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.5541. Min Act: -0.1700

Data Index: 1259136 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.4916. Min Act: -0.1700

Data Index: 439979 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.4291. Min Act: -0.1700

Data Index: 882276 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.3666. Min Act: -0.1696

Data Index: 1000491 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.3666. Min Act: -0.1700

Data Index: 1258498 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.3354. Min Act: -0.1700

Data Index: 1232042 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2729. Min Act: -0.1700

Data Index: 788893 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2416. Min Act: -0.1700

Data Index: 1119801 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2729. Min Act: -0.1700

Data Index: 1344392 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.3041. Min Act: -0.1700

Data Index: 773591 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2729. Min Act: -0.1700

Data Index: 434416 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2416. Min Act: -0.1700

Data Index: 1037867 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2104. Min Act: -0.1700

Data Index: 249527 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2104. Min Act: -0.1700

Data Index: 813349 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.1791. Min Act: -0.1700

Data Index: 386716 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.1791. Min Act: -0.1699

Data Index: 409686 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2416. Min Act: -0.1700

Data Index: 775791 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 5.6479. Min Range: -5.6479

Max Act: 5.2104. Min Act: -0.1700

Data Index: 889470 (C4 (Web Text))

Max Activating Token Index: 365