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

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

Neuron 749 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: 4.6176. Min Range: -4.6176

Max Act: 4.6176. Min Act: -0.1700

Data Index: 197866 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.4190. Min Act: -0.1700

Data Index: 940 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3979. Min Act: -0.1700

Data Index: 370807 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3422. Min Act: -0.1700

Data Index: 1158687 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3571. Min Act: -0.1700

Data Index: 301749 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3723. Min Act: -0.1700

Data Index: 752443 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3367. Min Act: -0.1700

Data Index: 913033 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3316. Min Act: -0.1700

Data Index: 570120 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3510. Min Act: -0.1700

Data Index: 125325 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3192. Min Act: -0.1700

Data Index: 837138 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3447. Min Act: -0.1700

Data Index: 102155 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3358. Min Act: -0.1700

Data Index: 891243 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.3593. Min Act: -0.1700

Data Index: 426467 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2994. Min Act: -0.1700

Data Index: 68821 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2830. Min Act: -0.1700

Data Index: 287223 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2890. Min Act: -0.1700

Data Index: 442862 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2632. Min Act: -0.1700

Data Index: 566603 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2765. Min Act: -0.1700

Data Index: 1114790 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2680. Min Act: -0.1700

Data Index: 360754 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 4.6176. Min Range: -4.6176

Max Act: 4.2916. Min Act: -0.1700

Data Index: 724785 (C4 (Web Text))

Max Activating Token Index: 153