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

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

Neuron 210 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: 3.4714. Min Range: -3.4714

Max Act: 3.4714. Min Act: -0.1694

Data Index: 123545 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.4518. Min Act: -0.1700

Data Index: 1543049 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.4049. Min Act: -0.1697

Data Index: 522701 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.3446. Min Act: -0.1700

Data Index: 1324644 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.3182. Min Act: -0.1699

Data Index: 1345463 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.3086. Min Act: -0.1699

Data Index: 554202 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.3111. Min Act: -0.1699

Data Index: 681377 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2840. Min Act: -0.1700

Data Index: 1633509 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2737. Min Act: -0.1697

Data Index: 759168 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2475. Min Act: -0.1700

Data Index: 1516787 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1451144 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2428. Min Act: -0.1700

Data Index: 687858 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2392. Min Act: -0.1691

Data Index: 577191 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2274. Min Act: -0.1700

Data Index: 385168 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2089. Min Act: -0.1700

Data Index: 1612346 (Python Code)

Max Activating Token Index: 671

Text #15

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2156. Min Act: -0.1700

Data Index: 305261 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.2126. Min Act: -0.1700

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.1948. Min Act: -0.1691

Data Index: 10029 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.1877. Min Act: -0.1700

Data Index: 1495363 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 3.4714. Min Range: -3.4714

Max Act: 3.1856. Min Act: -0.1677

Data Index: 1478788 (Python Code)

Max Activating Token Index: 224