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

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

Neuron 2030 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: 3.7655. Min Range: -3.7655

Max Act: 3.7655. Min Act: -0.1700

Data Index: 306026 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4994. Min Act: -0.1700

Data Index: 837230 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4994. Min Act: -0.1700

Data Index: 424383 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4837. Min Act: -0.1700

Data Index: 1227183 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4053. Min Act: -0.1700

Data Index: 628473 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4367. Min Act: -0.1700

Data Index: 1078786 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3896. Min Act: -0.1700

Data Index: 305626 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.2954. Min Act: -0.1700

Data Index: 18169 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4053. Min Act: -0.1700

Data Index: 874048 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4210. Min Act: -0.1700

Data Index: 474619 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3896. Min Act: -0.1700

Data Index: 142334 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3582. Min Act: -0.1700

Data Index: 993817 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.4367. Min Act: -0.1700

Data Index: 692205 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3425. Min Act: -0.1700

Data Index: 1310209 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3111. Min Act: -0.1700

Data Index: 1283445 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3425. Min Act: -0.1700

Data Index: 276525 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3268. Min Act: -0.1700

Data Index: 722789 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.3111. Min Act: -0.1700

Data Index: 643458 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.2640. Min Act: -0.1700

Data Index: 266616 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 3.7655. Min Range: -3.7655

Max Act: 3.2483. Min Act: -0.1700

Data Index: 399791 (C4 (Web Text))

Max Activating Token Index: 189