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

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

Neuron 456 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: 6.0383. Min Range: -6.0383

Max Act: 6.0383. Min Act: -0.1589

Data Index: 940347 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9750. Min Act: -0.1514

Data Index: 708979 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.9143. Min Act: -0.1317

Data Index: 29539 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8936. Min Act: -0.0892

Data Index: 805662 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8295. Min Act: -0.1690

Data Index: 553538 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8283. Min Act: -0.1700

Data Index: 907780 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8547. Min Act: -0.1700

Data Index: 321257 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7858. Min Act: -0.1698

Data Index: 1049300 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7681. Min Act: -0.1700

Data Index: 963353 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7730. Min Act: -0.1700

Data Index: 53663 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7858. Min Act: -0.1393

Data Index: 63606 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.8077. Min Act: -0.1699

Data Index: 1198649 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7933. Min Act: -0.1691

Data Index: 1264464 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7692. Min Act: -0.1625

Data Index: 431840 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7770. Min Act: -0.1366

Data Index: 878393 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7429. Min Act: -0.1700

Data Index: 573431 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7415. Min Act: -0.1699

Data Index: 91970 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.6928. Min Act: -0.0892

Data Index: 610079 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7382. Min Act: -0.1700

Data Index: 207138 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 6.0383. Min Range: -6.0383

Max Act: 5.7007. Min Act: -0.1232

Data Index: 143817 (C4 (Web Text))

Max Activating Token Index: 199