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

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

Neuron 1593 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: 3.4745. Min Range: -3.4745

Max Act: 3.4745. Min Act: -0.1677

Data Index: 399247 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.4108. Min Act: -0.1699

Data Index: 1177794 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.3448. Min Act: -0.1700

Data Index: 556301 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.3230. Min Act: -0.1700

Data Index: 413211 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.3269. Min Act: -0.1115

Data Index: 968600 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2882. Min Act: -0.1696

Data Index: 361672 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2848. Min Act: -0.1644

Data Index: 1225749 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2873. Min Act: -0.1626

Data Index: 1182280 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.3151. Min Act: -0.1699

Data Index: 718868 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2864. Min Act: -0.1661

Data Index: 453321 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2504. Min Act: -0.1697

Data Index: 1277097 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2594. Min Act: -0.1700

Data Index: 452128 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2656. Min Act: -0.0671

Data Index: 439761 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2541. Min Act: -0.1693

Data Index: 630316 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2692. Min Act: -0.1630

Data Index: 291035 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2540. Min Act: -0.1696

Data Index: 1021498 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2708. Min Act: -0.1675

Data Index: 1275727 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2520. Min Act: -0.1670

Data Index: 805646 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2489. Min Act: -0.1685

Data Index: 1072232 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 3.4745. Min Range: -3.4745

Max Act: 3.2246. Min Act: -0.1700

Data Index: 239613 (C4 (Web Text))

Max Activating Token Index: 461