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

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

Neuron 917 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: 3.7254. Min Range: -3.7254

Max Act: 3.7254. Min Act: -0.1700

Data Index: 1327189 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.6628. Min Act: -0.1700

Data Index: 1249534 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.6315. Min Act: -0.1700

Data Index: 57249 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.6628. Min Act: -0.1700

Data Index: 745565 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.6002. Min Act: -0.1700

Data Index: 414327 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4749. Min Act: -0.1700

Data Index: 60679 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1131076 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4435. Min Act: -0.1700

Data Index: 849651 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4435. Min Act: -0.1700

Data Index: 985167 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1128976 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4435. Min Act: -0.1700

Data Index: 344956 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4435. Min Act: -0.1700

Data Index: 430772 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4121. Min Act: -0.1700

Data Index: 501162 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.4121. Min Act: -0.1700

Data Index: 1098738 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3808. Min Act: -0.1700

Data Index: 124797 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3494. Min Act: -0.1700

Data Index: 159316 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1250440 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3808. Min Act: -0.1700

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3808. Min Act: -0.1700

Data Index: 988181 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3494. Min Act: -0.1700

Data Index: 858218 (C4 (Web Text))

Max Activating Token Index: 645