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

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

Neuron 1961 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: 5.8947. Min Range: -5.8947

Max Act: 5.8947. Min Act: -0.1700

Data Index: 190941 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.7072. Min Act: -0.1700

Data Index: 497013 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.7384. Min Act: -0.1700

Data Index: 243627 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.7072. Min Act: -0.1700

Data Index: 1191926 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6447. Min Act: -0.1700

Data Index: 694381 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6447. Min Act: -0.1700

Data Index: 933677 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6759. Min Act: -0.1700

Data Index: 552087 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6134. Min Act: -0.1700

Data Index: 1062556 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6134. Min Act: -0.1700

Data Index: 490126 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6134. Min Act: -0.1700

Data Index: 273255 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.5822. Min Act: -0.1700

Data Index: 812642 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6134. Min Act: -0.1700

Data Index: 1136252 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.6134. Min Act: -0.1700

Data Index: 354091 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.5822. Min Act: -0.1700

Data Index: 886129 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.5197. Min Act: -0.1700

Data Index: 1012113 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.5509. Min Act: -0.1700

Data Index: 478090 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.5197. Min Act: -0.1700

Data Index: 1308749 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.5197. Min Act: -0.1700

Data Index: 882910 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.4884. Min Act: -0.1700

Data Index: 691381 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 5.8947. Min Range: -5.8947

Max Act: 5.4572. Min Act: -0.1700

Data Index: 1216073 (C4 (Web Text))

Max Activating Token Index: 525