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

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

Neuron 1626 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.7835. Min Act: -0.1700

Data Index: 164700 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.7678. Min Act: -0.1700

Data Index: 487038 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6583. Min Act: -0.1700

Data Index: 42761 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6740. Min Act: -0.1700

Data Index: 313136 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6270. Min Act: -0.1700

Data Index: 409298 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6270. Min Act: -0.1700

Data Index: 1219601 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6270. Min Act: -0.1700

Data Index: 89120 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6270. Min Act: -0.1700

Data Index: 1156193 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5644. Min Act: -0.1700

Data Index: 861354 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 678863 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 1266998 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 707557 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1177446 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 790319 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 922943 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5331. Min Act: -0.1700

Data Index: 1114259 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 538766 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5487. Min Act: -0.1700

Data Index: 1189584 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.5331. Min Act: -0.1700

Data Index: 1301164 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.7835. Min Range: -3.7835

Max Act: 3.4704. Min Act: -0.1700

Data Index: 1176340 (C4 (Web Text))

Max Activating Token Index: 886