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

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

Neuron 502 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: 3.5204. Min Range: -3.5204

Max Act: 3.5204. Min Act: -0.1700

Data Index: 1017486 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.4107. Min Act: -0.1700

Data Index: 1124989 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3950. Min Act: -0.1700

Data Index: 578361 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3793. Min Act: -0.1700

Data Index: 727307 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1031890 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3479. Min Act: -0.1700

Data Index: 607564 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3793. Min Act: -0.1700

Data Index: 38784 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3636. Min Act: -0.1700

Data Index: 193972 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3322. Min Act: -0.1700

Data Index: 822763 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3322. Min Act: -0.1700

Data Index: 208321 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3322. Min Act: -0.1700

Data Index: 1309661 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3322. Min Act: -0.1700

Data Index: 85915 (C4 (Web Text))

Max Activating Token Index: 76

Text #12

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3008. Min Act: -0.1700

Data Index: 21138 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3165. Min Act: -0.1700

Data Index: 726831 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1163646 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.3008. Min Act: -0.1700

Data Index: 1296631 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.2851. Min Act: -0.1700

Data Index: 415497 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.2851. Min Act: -0.1700

Data Index: 194756 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.2851. Min Act: -0.1700

Data Index: 137631 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.5204. Min Range: -3.5204

Max Act: 3.2851. Min Act: -0.1700

Data Index: 466772 (C4 (Web Text))

Max Activating Token Index: 253