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

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

Neuron 1625 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.5693. Min Act: -0.1700

Data Index: 11455 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4596. Min Act: -0.1700

Data Index: 1149542 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4283. Min Act: -0.1700

Data Index: 248007 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4126. Min Act: -0.1700

Data Index: 202403 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4283. Min Act: -0.1700

Data Index: 100763 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4126. Min Act: -0.1700

Data Index: 82694 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4283. Min Act: -0.1700

Data Index: 1008337 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.4126. Min Act: -0.1700

Data Index: 637013 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3969. Min Act: -0.1700

Data Index: 477952 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1199095 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3969. Min Act: -0.1700

Data Index: 454726 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3812. Min Act: -0.1700

Data Index: 1304215 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3969. Min Act: -0.1700

Data Index: 183584 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3812. Min Act: -0.1700

Data Index: 415720 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1003815 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1145535 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3655. Min Act: -0.1700

Data Index: 341563 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3655. Min Act: -0.1700

Data Index: 1031796 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3655. Min Act: -0.1700

Data Index: 205122 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 3.5693. Min Range: -3.5693

Max Act: 3.3812. Min Act: -0.1700

Data Index: 1217252 (C4 (Web Text))

Max Activating Token Index: 95