Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 341 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0077. Min Range: -3.0077

Max Act: 3.0077. Min Act: -0.1700

Data Index: 152205 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.9286. Min Act: -0.1700

Data Index: 12727 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.9286. Min Act: -0.1700

Data Index: 1249739 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.9128. Min Act: -0.1700

Data Index: 1577811 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.9128. Min Act: -0.1700

Data Index: 190302 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.9128. Min Act: -0.1700

Data Index: 1203334 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.9128. Min Act: -0.1700

Data Index: 759571 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8810. Min Act: -0.1700

Data Index: 1084986 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8810. Min Act: -0.1700

Data Index: 1076060 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8652. Min Act: -0.1700

Data Index: 618169 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8652. Min Act: -0.1700

Data Index: 236684 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8493. Min Act: -0.1700

Data Index: 723386 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8652. Min Act: -0.1700

Data Index: 1367874 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8493. Min Act: -0.1700

Data Index: 983406 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8493. Min Act: -0.1700

Data Index: 1142379 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8334. Min Act: -0.1700

Data Index: 1382671 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8334. Min Act: -0.1700

Data Index: 120540 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8175. Min Act: -0.1700

Data Index: 997496 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8175. Min Act: -0.1700

Data Index: 1249891 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 3.0077. Min Range: -3.0077

Max Act: 2.8015. Min Act: -0.1700

Data Index: 89459 (C4 (Web Text))

Max Activating Token Index: 781