Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 233 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.6001. Min Act: -0.1367

Data Index: 852520 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5639. Min Act: -0.1525

Data Index: 623875 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5729. Min Act: -0.1700

Data Index: 442484 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5029. Min Act: -0.1700

Data Index: 208949 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4905. Min Act: -0.1563

Data Index: 707385 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4715. Min Act: -0.0734

Data Index: 1048416 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4693. Min Act: -0.1700

Data Index: 646911 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4803. Min Act: -0.1700

Data Index: 372734 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4583. Min Act: -0.1647

Data Index: 919266 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4572. Min Act: -0.1698

Data Index: 785472 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4298. Min Act: -0.1694

Data Index: 1004510 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4327. Min Act: -0.1532

Data Index: 110589 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4379. Min Act: -0.1035

Data Index: 1062227 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4548. Min Act: -0.1284

Data Index: 30462 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4279. Min Act: -0.1690

Data Index: 418625 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4277. Min Act: -0.1698

Data Index: 1287330 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4252. Min Act: -0.1698

Data Index: 196447 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4262. Min Act: -0.1700

Data Index: 947157 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4022. Min Act: -0.1586

Data Index: 341275 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.4111. Min Act: -0.1481

Data Index: 380098 (C4 (Web Text))

Max Activating Token Index: 560