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

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

Neuron 153 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.2535. Min Act: -0.1700

Data Index: 1223200 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.2378. Min Act: -0.1700

Data Index: 1002672 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.2221. Min Act: -0.1700

Data Index: 26239 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1906. Min Act: -0.1700

Data Index: 1056202 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1749. Min Act: -0.1700

Data Index: 1176381 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.2064. Min Act: -0.1700

Data Index: 429769 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1749. Min Act: -0.1700

Data Index: 124389 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1749. Min Act: -0.1700

Data Index: 986234 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1749. Min Act: -0.1700

Data Index: 5783 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1906. Min Act: -0.1700

Data Index: 306936 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1749. Min Act: -0.1700

Data Index: 549782 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1592. Min Act: -0.1700

Data Index: 156431 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1434. Min Act: -0.1700

Data Index: 625503 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1434. Min Act: -0.1700

Data Index: 1349515 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1749. Min Act: -0.1700

Data Index: 233854 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1434. Min Act: -0.1700

Data Index: 1167267 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1434. Min Act: -0.1700

Data Index: 863646 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1434. Min Act: -0.1700

Data Index: 413695 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1434. Min Act: -0.1700

Data Index: 1269314 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.2535. Min Range: -3.2535

Max Act: 3.1119. Min Act: -0.1700

Data Index: 986359 (C4 (Web Text))

Max Activating Token Index: 70