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

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

Neuron 78 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: 3.8373. Min Range: -3.8373

Max Act: 3.8373. Min Act: -0.1700

Data Index: 770931 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.8121. Min Act: -0.1700

Data Index: 488064 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.8104. Min Act: -0.1700

Data Index: 769876 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.7897. Min Act: -0.1700

Data Index: 1402454 (Python Code)

Max Activating Token Index: 319

Text #4

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.7538. Min Act: -0.1700

Data Index: 1585601 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.7587. Min Act: -0.1700

Data Index: 1203223 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.7256. Min Act: -0.1700

Data Index: 611403 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.7378. Min Act: -0.1700

Data Index: 488576 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.7023. Min Act: -0.1700

Data Index: 1326739 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6897. Min Act: -0.1700

Data Index: 1391419 (Python Code)

Max Activating Token Index: 873

Text #10

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6520. Min Act: -0.1700

Data Index: 801109 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6452. Min Act: -0.1700

Data Index: 1571071 (Python Code)

Max Activating Token Index: 977

Text #12

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1655531 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5936. Min Act: -0.1700

Data Index: 1609783 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5949. Min Act: -0.1700

Data Index: 1569981 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6099. Min Act: -0.1700

Data Index: 358176 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.6076. Min Act: -0.1700

Data Index: 618647 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5898. Min Act: -0.1700

Data Index: 1627709 (Python Code)

Max Activating Token Index: 794

Text #18

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5834. Min Act: -0.1700

Data Index: 1006500 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 3.8373. Min Range: -3.8373

Max Act: 3.5833. Min Act: -0.1700

Data Index: 1633774 (Python Code)

Max Activating Token Index: 569