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

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

Neuron 528 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: 3.7488. Min Range: -3.7488

Max Act: 3.7019. Min Act: -0.1700

Data Index: 147906 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.7488. Min Act: -0.1700

Data Index: 1061972 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.7488. Min Act: -0.1700

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6549. Min Act: -0.1700

Data Index: 87266 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6706. Min Act: -0.1700

Data Index: 313810 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1402747 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6549. Min Act: -0.1700

Data Index: 1428531 (Python Code)

Max Activating Token Index: 536

Text #7

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.5453. Min Act: -0.1700

Data Index: 206744 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.7175. Min Act: -0.1700

Data Index: 204091 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1622382 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.5767. Min Act: -0.1700

Data Index: 843458 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1614972 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.5923. Min Act: -0.1700

Data Index: 1122428 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6706. Min Act: -0.1700

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6080. Min Act: -0.1700

Data Index: 371324 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6080. Min Act: -0.1700

Data Index: 870811 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.5923. Min Act: -0.1700

Data Index: 165408 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.4827. Min Act: -0.1700

Data Index: 624064 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6236. Min Act: -0.1700

Data Index: 1586574 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 3.7488. Min Range: -3.7488

Max Act: 3.6080. Min Act: -0.1700

Data Index: 1536564 (Python Code)

Max Activating Token Index: 70