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

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

Neuron 631 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6060. Min Act: -0.1700

Data Index: 615831 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6060. Min Act: -0.1700

Data Index: 523768 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6374. Min Act: -0.1700

Data Index: 632948 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5747. Min Act: -0.1700

Data Index: 634007 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6060. Min Act: -0.1700

Data Index: 872093 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5747. Min Act: -0.1700

Data Index: 618272 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6060. Min Act: -0.1700

Data Index: 648086 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6060. Min Act: -0.1700

Data Index: 931599 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1108791 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1233547 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5434. Min Act: -0.1700

Data Index: 470007 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5277. Min Act: -0.1700

Data Index: 481594 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5121. Min Act: -0.1700

Data Index: 1077437 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4807. Min Act: -0.1700

Data Index: 835171 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4807. Min Act: -0.1700

Data Index: 831491 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4807. Min Act: -0.1700

Data Index: 174488 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4651. Min Act: -0.1700

Data Index: 270513 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4651. Min Act: -0.1700

Data Index: 513310 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4807. Min Act: -0.1700

Data Index: 467688 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4807. Min Act: -0.1700

Data Index: 92076 (C4 (Web Text))

Max Activating Token Index: 22