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

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

Neuron 1840 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: 5.5058. Min Range: -5.5058

Max Act: 5.5058. Min Act: -0.1700

Data Index: 548583 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.4433. Min Act: -0.1700

Data Index: 253280 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3808. Min Act: -0.1700

Data Index: 545201 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3808. Min Act: -0.1699

Data Index: 201919 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.4121. Min Act: -0.1700

Data Index: 1205725 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 158389 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3496. Min Act: -0.1700

Data Index: 782848 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.4121. Min Act: -0.1700

Data Index: 345792 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 3424 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 916743 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 1076846 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 1349014 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.2871. Min Act: -0.1700

Data Index: 205156 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 613716 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.3183. Min Act: -0.1700

Data Index: 273361 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.2871. Min Act: -0.1700

Data Index: 349582 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.2558. Min Act: -0.1700

Data Index: 812589 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.2871. Min Act: -0.1700

Data Index: 717515 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.2871. Min Act: -0.1700

Data Index: 821784 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 5.5058. Min Range: -5.5058

Max Act: 5.2871. Min Act: -0.1700

Data Index: 757395 (C4 (Web Text))

Max Activating Token Index: 234