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

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

Neuron 358 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2102. Min Range: -4.2102

Max Act: 4.2102. Min Act: -0.1700

Data Index: 130589 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 4.2102. Min Range: -4.2102

Max Act: 4.1477. Min Act: -0.1700

Data Index: 529070 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 4.2102. Min Range: -4.2102

Max Act: 4.1477. Min Act: -0.1700

Data Index: 475069 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.9913. Min Act: -0.1700

Data Index: 109483 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.9601. Min Act: -0.1700

Data Index: 976898 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.7724. Min Act: -0.1700

Data Index: 539231 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.9288. Min Act: -0.1700

Data Index: 990446 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8663. Min Act: -0.1700

Data Index: 725857 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8037. Min Act: -0.1700

Data Index: 256045 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8037. Min Act: -0.1700

Data Index: 788714 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8350. Min Act: -0.1700

Data Index: 1070503 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8663. Min Act: -0.1700

Data Index: 714637 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.7724. Min Act: -0.1700

Data Index: 54165 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8663. Min Act: -0.1700

Data Index: 831062 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8037. Min Act: -0.1700

Data Index: 972157 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8037. Min Act: -0.1700

Data Index: 743279 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8663. Min Act: -0.1700

Data Index: 492838 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8037. Min Act: -0.1700

Data Index: 389326 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.8350. Min Act: -0.1700

Data Index: 933835 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 4.2102. Min Range: -4.2102

Max Act: 3.7411. Min Act: -0.1700

Data Index: 5243 (C4 (Web Text))

Max Activating Token Index: 299