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

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

Neuron 1524 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: 4.3406. Min Range: -4.3406

Max Act: 4.3406. Min Act: -0.1700

Data Index: 1494218 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2723. Min Act: -0.1700

Data Index: 737731 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2901. Min Act: -0.1700

Data Index: 686683 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2344. Min Act: -0.1700

Data Index: 1517945 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2688. Min Act: -0.1700

Data Index: 1016678 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2492. Min Act: -0.1700

Data Index: 1367193 (Python Code)

Max Activating Token Index: 524

Text #6

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2040. Min Act: -0.1700

Data Index: 1232400 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2369. Min Act: -0.1700

Data Index: 588353 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2315. Min Act: -0.1700

Data Index: 307896 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2410. Min Act: -0.1700

Data Index: 316731 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1977. Min Act: -0.1700

Data Index: 1141585 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2509. Min Act: -0.1700

Data Index: 706776 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2460. Min Act: -0.1700

Data Index: 970900 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1856. Min Act: -0.1700

Data Index: 1463437 (Python Code)

Max Activating Token Index: 454

Text #14

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1507. Min Act: -0.1700

Data Index: 1530687 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1800. Min Act: -0.1700

Data Index: 500767 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1948. Min Act: -0.1700

Data Index: 1316946 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1368. Min Act: -0.1700

Data Index: 92003 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.1380. Min Act: -0.1700

Data Index: 791894 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 4.3406. Min Range: -4.3406

Max Act: 4.2017. Min Act: -0.1700

Data Index: 485036 (C4 (Web Text))

Max Activating Token Index: 488