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

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

Neuron 2040 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: 3.1360. Min Range: -3.1360

Max Act: 3.1360. Min Act: -0.1700

Data Index: 1068611 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1360. Min Act: -0.1700

Data Index: 1253426 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1360. Min Act: -0.1700

Data Index: 830263 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 413461 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 394915 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 638471 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 1019066 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1044. Min Act: -0.1700

Data Index: 6633 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 1309232 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 1117828 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1202. Min Act: -0.1700

Data Index: 482955 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0887. Min Act: -0.1700

Data Index: 652018 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0887. Min Act: -0.1700

Data Index: 1086124 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0887. Min Act: -0.1700

Data Index: 361358 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0887. Min Act: -0.1700

Data Index: 228668 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1044. Min Act: -0.1700

Data Index: 1120730 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.1044. Min Act: -0.1700

Data Index: 544233 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0887. Min Act: -0.1700

Data Index: 1137307 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0729. Min Act: -0.1700

Data Index: 187807 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 3.1360. Min Range: -3.1360

Max Act: 3.0887. Min Act: -0.1700

Data Index: 174410 (C4 (Web Text))

Max Activating Token Index: 70