Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1429 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.5771. Min Act: -0.1700

Data Index: 253579 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.5145. Min Act: -0.1700

Data Index: 1152599 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.5458. Min Act: -0.1700

Data Index: 325568 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4361. Min Act: -0.1700

Data Index: 1077860 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4831. Min Act: -0.1700

Data Index: 973993 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4518. Min Act: -0.1700

Data Index: 327352 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4204. Min Act: -0.1700

Data Index: 202535 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4047. Min Act: -0.1700

Data Index: 204728 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4518. Min Act: -0.1700

Data Index: 690386 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4204. Min Act: -0.1700

Data Index: 195572 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3577. Min Act: -0.1700

Data Index: 958717 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3734. Min Act: -0.1700

Data Index: 1101496 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.4361. Min Act: -0.1700

Data Index: 440007 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3420. Min Act: -0.1700

Data Index: 1051032 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3263. Min Act: -0.1700

Data Index: 560276 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3106. Min Act: -0.1700

Data Index: 663995 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3420. Min Act: -0.1700

Data Index: 1060161 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3890. Min Act: -0.1700

Data Index: 559143 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3106. Min Act: -0.1700

Data Index: 949553 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.5771. Min Range: -3.5771

Max Act: 3.3420. Min Act: -0.1700

Data Index: 1010381 (C4 (Web Text))

Max Activating Token Index: 967