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

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

Neuron 521 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.3546. Min Act: -0.1700

Data Index: 1315563 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.3546. Min Act: -0.1700

Data Index: 67304 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2760. Min Act: -0.1700

Data Index: 1204224 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2760. Min Act: -0.1700

Data Index: 681171 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2603. Min Act: -0.1700

Data Index: 800991 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2603. Min Act: -0.1700

Data Index: 765949 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2289. Min Act: -0.1700

Data Index: 580333 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2289. Min Act: -0.1700

Data Index: 304388 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2289. Min Act: -0.1700

Data Index: 500831 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2289. Min Act: -0.1700

Data Index: 401371 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2446. Min Act: -0.1700

Data Index: 696969 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2132. Min Act: -0.1700

Data Index: 1107453 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1974. Min Act: -0.1700

Data Index: 801840 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1974. Min Act: -0.1700

Data Index: 685773 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.2132. Min Act: -0.1700

Data Index: 85037 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1817. Min Act: -0.1700

Data Index: 213460 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1817. Min Act: -0.1700

Data Index: 63310 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1817. Min Act: -0.1700

Data Index: 1176827 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1011867 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 3.3546. Min Range: -3.3546

Max Act: 3.1817. Min Act: -0.1700

Data Index: 502216 (C4 (Web Text))

Max Activating Token Index: 253