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

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

Neuron 992 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: 5.9382. Min Range: -5.9382

Max Act: 5.9382. Min Act: -0.1700

Data Index: 697078 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.8757. Min Act: -0.1700

Data Index: 598555 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.8757. Min Act: -0.1700

Data Index: 132703 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.7507. Min Act: -0.1700

Data Index: 107941 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.8132. Min Act: -0.1700

Data Index: 924241 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.8445. Min Act: -0.1700

Data Index: 253456 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.7195. Min Act: -0.1700

Data Index: 1090716 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.7195. Min Act: -0.1700

Data Index: 725369 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.7507. Min Act: -0.1700

Data Index: 1254550 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6257. Min Act: -0.1700

Data Index: 1161888 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6882. Min Act: -0.1700

Data Index: 317833 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6570. Min Act: -0.1700

Data Index: 1305218 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6257. Min Act: -0.1700

Data Index: 573326 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.5945. Min Act: -0.1700

Data Index: 212190 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6570. Min Act: -0.1700

Data Index: 997382 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.5945. Min Act: -0.1700

Data Index: 1080241 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.5632. Min Act: -0.1700

Data Index: 1293141 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6257. Min Act: -0.1700

Data Index: 1320457 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.6257. Min Act: -0.1700

Data Index: 252026 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 5.9382. Min Range: -5.9382

Max Act: 5.5632. Min Act: -0.1700

Data Index: 514283 (C4 (Web Text))

Max Activating Token Index: 246