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

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

Neuron 1257 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: 4.0445. Min Range: -4.0445

Max Act: 4.0445. Min Act: -0.1699

Data Index: 1456162 (Python Code)

Max Activating Token Index: 609

Text #1

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.9651. Min Act: -0.1700

Data Index: 729772 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.9376. Min Act: -0.1699

Data Index: 1512894 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.8782. Min Act: -0.1699

Data Index: 1307456 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.9128. Min Act: -0.1700

Data Index: 1199379 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.8740. Min Act: -0.1700

Data Index: 242472 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.8516. Min Act: -0.1641

Data Index: 1591742 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.8583. Min Act: -0.1700

Data Index: 201053 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.8425. Min Act: -0.1699

Data Index: 1597742 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7777. Min Act: -0.1696

Data Index: 1123520 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.8032. Min Act: -0.1700

Data Index: 1578172 (Python Code)

Max Activating Token Index: 971

Text #11

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7955. Min Act: -0.1700

Data Index: 56839 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7891. Min Act: -0.1700

Data Index: 1267776 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7928. Min Act: -0.1700

Data Index: 911526 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7567. Min Act: -0.1700

Data Index: 546022 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7732. Min Act: -0.1698

Data Index: 1410778 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7635. Min Act: -0.1690

Data Index: 1385501 (Python Code)

Max Activating Token Index: 745

Text #17

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7985. Min Act: -0.1699

Data Index: 1009097 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7674. Min Act: -0.1699

Data Index: 600064 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 4.0445. Min Range: -4.0445

Max Act: 3.7669. Min Act: -0.1700

Data Index: 1237689 (C4 (Web Text))

Max Activating Token Index: 776