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

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

Neuron 1253 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: 3.0702. Min Range: -3.0702

Max Act: 3.0702. Min Act: -0.1700

Data Index: 575153 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9651. Min Act: -0.1700

Data Index: 373881 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9781. Min Act: -0.1700

Data Index: 1402662 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9534. Min Act: -0.1700

Data Index: 489450 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9186. Min Act: -0.1700

Data Index: 828698 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8847. Min Act: -0.1700

Data Index: 212893 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.9000. Min Act: -0.1700

Data Index: 135878 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8954. Min Act: -0.1700

Data Index: 130067 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8659. Min Act: -0.1699

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8689. Min Act: -0.1700

Data Index: 445480 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8663. Min Act: -0.1700

Data Index: 93413 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8732. Min Act: -0.1700

Data Index: 1070527 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8475. Min Act: -0.1700

Data Index: 1636515 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8614. Min Act: -0.1700

Data Index: 1508619 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8584. Min Act: -0.1700

Data Index: 1650375 (Python Code)

Max Activating Token Index: 129

Text #15

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8522. Min Act: -0.1700

Data Index: 1293956 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8474. Min Act: -0.1686

Data Index: 1019648 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8433. Min Act: -0.1700

Data Index: 1426446 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8380. Min Act: -0.1700

Data Index: 1624035 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 3.0702. Min Range: -3.0702

Max Act: 2.8109. Min Act: -0.1700

Data Index: 66520 (C4 (Web Text))

Max Activating Token Index: 309