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

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

Neuron 168 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: 3.8131. Min Range: -3.8131

Max Act: 3.8131. Min Act: -0.1700

Data Index: 1108804 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.6880. Min Act: -0.1700

Data Index: 671269 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5940. Min Act: -0.1700

Data Index: 1171939 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.6567. Min Act: -0.1700

Data Index: 414484 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.6567. Min Act: -0.1700

Data Index: 1001489 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.6253. Min Act: -0.1700

Data Index: 162645 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5940. Min Act: -0.1700

Data Index: 340370 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5940. Min Act: -0.1700

Data Index: 1178830 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5627. Min Act: -0.1700

Data Index: 551491 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5940. Min Act: -0.1700

Data Index: 602211 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.6253. Min Act: -0.1700

Data Index: 1157595 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5314. Min Act: -0.1700

Data Index: 1285947 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5940. Min Act: -0.1700

Data Index: 165739 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5627. Min Act: -0.1700

Data Index: 1316724 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5627. Min Act: -0.1700

Data Index: 885137 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5314. Min Act: -0.1700

Data Index: 190354 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5314. Min Act: -0.1700

Data Index: 1213615 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5314. Min Act: -0.1700

Data Index: 730048 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5001. Min Act: -0.1700

Data Index: 61873 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 3.8131. Min Range: -3.8131

Max Act: 3.5001. Min Act: -0.1700

Data Index: 1326964 (C4 (Web Text))

Max Activating Token Index: 670