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

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

Neuron 903 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: 4.3646. Min Range: -4.3646

Max Act: 4.3646. Min Act: -0.1141

Data Index: 1431404 (Python Code)

Max Activating Token Index: 861

Text #1

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.1769. Min Act: -0.1471

Data Index: 1506897 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.0740. Min Act: -0.1700

Data Index: 990799 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.0483. Min Act: -0.1700

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 4.3646. Min Range: -4.3646

Max Act: 4.0308. Min Act: -0.1700

Data Index: 1321272 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.9378. Min Act: -0.0968

Data Index: 540756 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8648. Min Act: -0.1700

Data Index: 224891 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.9094. Min Act: -0.1477

Data Index: 1462046 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.9194. Min Act: -0.1693

Data Index: 1489211 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8829. Min Act: -0.1644

Data Index: 1366762 (Python Code)

Max Activating Token Index: 687

Text #10

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8659. Min Act: -0.1683

Data Index: 1506098 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8479. Min Act: -0.1624

Data Index: 70604 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8368. Min Act: -0.1700

Data Index: 1501507 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8508. Min Act: -0.1008

Data Index: 1568338 (Python Code)

Max Activating Token Index: 867

Text #14

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8351. Min Act: -0.1700

Data Index: 104082 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8613. Min Act: -0.1685

Data Index: 853516 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8276. Min Act: -0.1700

Data Index: 1222845 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8271. Min Act: -0.1700

Data Index: 1643518 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.8362. Min Act: -0.1700

Data Index: 552006 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 4.3646. Min Range: -4.3646

Max Act: 3.7920. Min Act: -0.1700

Data Index: 306493 (C4 (Web Text))

Max Activating Token Index: 650