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

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

Neuron 1559 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: 4.0359. Min Range: -4.0359

Max Act: 4.0359. Min Act: -0.1673

Data Index: 1172761 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.9646. Min Act: -0.1700

Data Index: 469020 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.9374. Min Act: -0.1617

Data Index: 372764 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.9087. Min Act: -0.1700

Data Index: 1132295 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8465. Min Act: -0.1700

Data Index: 289977 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8634. Min Act: -0.1700

Data Index: 248653 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8638. Min Act: -0.1700

Data Index: 522960 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8420. Min Act: -0.1700

Data Index: 938324 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8457. Min Act: -0.1700

Data Index: 429212 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8192. Min Act: -0.1700

Data Index: 876521 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8155. Min Act: -0.1700

Data Index: 103840 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8282. Min Act: -0.1700

Data Index: 393689 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8038. Min Act: -0.1700

Data Index: 669803 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.8129. Min Act: -0.1700

Data Index: 995297 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.7988. Min Act: -0.1700

Data Index: 978908 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.7873. Min Act: -0.1660

Data Index: 1219901 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.7873. Min Act: -0.1700

Data Index: 689591 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.7849. Min Act: -0.1700

Data Index: 1107860 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 4.0359. Min Range: -4.0359

Max Act: 3.7479. Min Act: -0.1700

Data Index: 622627 (C4 (Web Text))

Max Activating Token Index: 890