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

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

Neuron 374 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.9320. Min Act: -0.1700

Data Index: 1062499 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.9320. Min Act: -0.1700

Data Index: 299470 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.9150. Min Act: -0.1700

Data Index: 1235635 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8980. Min Act: -0.1700

Data Index: 704294 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8980. Min Act: -0.1700

Data Index: 912313 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8809. Min Act: -0.1700

Data Index: 866835 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8638. Min Act: -0.1700

Data Index: 369408 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8638. Min Act: -0.1700

Data Index: 1363608 (Python Code)

Max Activating Token Index: 796

Text #8

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8467. Min Act: -0.1700

Data Index: 836726 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8638. Min Act: -0.1700

Data Index: 370398 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8467. Min Act: -0.1700

Data Index: 731459 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8467. Min Act: -0.1700

Data Index: 931805 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8296. Min Act: -0.1700

Data Index: 251682 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8467. Min Act: -0.1700

Data Index: 617101 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8296. Min Act: -0.1700

Data Index: 414237 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8467. Min Act: -0.1700

Data Index: 1268098 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8296. Min Act: -0.1700

Data Index: 435794 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8210. Min Act: -0.1700

Data Index: 1036256 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8296. Min Act: -0.1700

Data Index: 542652 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.9320. Min Range: -1.9320

Max Act: 1.8296. Min Act: -0.1700

Data Index: 621971 (C4 (Web Text))

Max Activating Token Index: 742