Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 342 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.9511. Min Act: -0.1700

Data Index: 5380 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.8729. Min Act: -0.1700

Data Index: 311649 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.8416. Min Act: -0.1700

Data Index: 881652 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.8416. Min Act: -0.1700

Data Index: 1119050 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7634. Min Act: -0.1700

Data Index: 133762 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7321. Min Act: -0.1700

Data Index: 669675 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7165. Min Act: -0.1700

Data Index: 445196 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7008. Min Act: -0.1700

Data Index: 1052314 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7165. Min Act: -0.1700

Data Index: 721053 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7165. Min Act: -0.1700

Data Index: 438725 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7165. Min Act: -0.1700

Data Index: 1035878 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7321. Min Act: -0.1700

Data Index: 757844 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6852. Min Act: -0.1700

Data Index: 989744 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.7165. Min Act: -0.1700

Data Index: 1057456 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6852. Min Act: -0.1700

Data Index: 139288 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6539. Min Act: -0.1700

Data Index: 632984 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6539. Min Act: -0.1700

Data Index: 1303688 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6695. Min Act: -0.1700

Data Index: 1062498 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6695. Min Act: -0.1700

Data Index: 122139 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 3.9511. Min Range: -3.9511

Max Act: 3.6539. Min Act: -0.1700

Data Index: 626754 (C4 (Web Text))

Max Activating Token Index: 833