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

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

Neuron 1842 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: 3.7095. Min Range: -3.7095

Max Act: 3.7095. Min Act: -0.1700

Data Index: 1149180 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.6782. Min Act: -0.1700

Data Index: 1606741 (Python Code)

Max Activating Token Index: 937

Text #2

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.6469. Min Act: -0.1700

Data Index: 269498 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5842. Min Act: -0.1700

Data Index: 1244521 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5686. Min Act: -0.1700

Data Index: 1002017 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5842. Min Act: -0.1700

Data Index: 1391775 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5373. Min Act: -0.1700

Data Index: 860020 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5529. Min Act: -0.1700

Data Index: 884911 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5216. Min Act: -0.1700

Data Index: 951784 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5529. Min Act: -0.1700

Data Index: 236075 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5216. Min Act: -0.1700

Data Index: 1225878 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5059. Min Act: -0.1700

Data Index: 788754 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5059. Min Act: -0.1700

Data Index: 863228 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5216. Min Act: -0.1700

Data Index: 538288 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5059. Min Act: -0.1700

Data Index: 395402 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5216. Min Act: -0.1700

Data Index: 66351 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.4903. Min Act: -0.1700

Data Index: 945676 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.4903. Min Act: -0.1700

Data Index: 463854 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.5059. Min Act: -0.1700

Data Index: 1568754 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 3.7095. Min Range: -3.7095

Max Act: 3.4903. Min Act: -0.1700

Data Index: 276747 (C4 (Web Text))

Max Activating Token Index: 44