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

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

Neuron 1661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.9484. Min Act: -0.1700

Data Index: 580449 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.9484. Min Act: -0.1700

Data Index: 1040003 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.9172. Min Act: -0.1700

Data Index: 13625 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.9172. Min Act: -0.1700

Data Index: 846899 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.9172. Min Act: -0.1700

Data Index: 1034409 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.8234. Min Act: -0.1700

Data Index: 1349023 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.7609. Min Act: -0.1700

Data Index: 174327 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.8234. Min Act: -0.1700

Data Index: 1289201 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6984. Min Act: -0.1700

Data Index: 945089 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.7297. Min Act: -0.1700

Data Index: 519079 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.7609. Min Act: -0.1700

Data Index: 156239 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6984. Min Act: -0.1700

Data Index: 248241 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.7609. Min Act: -0.1700

Data Index: 30023 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.7297. Min Act: -0.1700

Data Index: 1112221 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6359. Min Act: -0.1700

Data Index: 487828 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6672. Min Act: -0.1699

Data Index: 982487 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6984. Min Act: -0.1700

Data Index: 729992 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6359. Min Act: -0.1700

Data Index: 1206515 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6984. Min Act: -0.1700

Data Index: 974176 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 5.9484. Min Range: -5.9484

Max Act: 5.6359. Min Act: -0.1700

Data Index: 1052283 (C4 (Web Text))

Max Activating Token Index: 575