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

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

Neuron 1093 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0667. Min Act: -0.1700

Data Index: 181280 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0198. Min Act: -0.1700

Data Index: 369767 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0198. Min Act: -0.1700

Data Index: 1612053 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0041. Min Act: -0.1700

Data Index: 268733 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 4.0667. Min Range: -4.0667

Max Act: 4.0198. Min Act: -0.1699

Data Index: 24233 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9729. Min Act: -0.1700

Data Index: 662900 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9416. Min Act: -0.1693

Data Index: 232692 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9260. Min Act: -0.1700

Data Index: 154461 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9260. Min Act: -0.1700

Data Index: 932208 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9260. Min Act: -0.1700

Data Index: 186137 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.9103. Min Act: -0.1700

Data Index: 389381 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8947. Min Act: -0.1700

Data Index: 762692 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8791. Min Act: -0.1700

Data Index: 783933 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8947. Min Act: -0.1700

Data Index: 562031 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8634. Min Act: -0.1699

Data Index: 1246835 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8478. Min Act: -0.1700

Data Index: 1038688 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8947. Min Act: -0.1700

Data Index: 632403 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8947. Min Act: -0.1700

Data Index: 299896 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8791. Min Act: -0.1700

Data Index: 313874 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 4.0667. Min Range: -4.0667

Max Act: 3.8321. Min Act: -0.1700

Data Index: 614471 (C4 (Web Text))

Max Activating Token Index: 17