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

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

Neuron 667 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: 3.1385. Min Range: -3.1385

Max Act: 3.1385. Min Act: -0.1700

Data Index: 354706 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.1070. Min Act: -0.1700

Data Index: 24165 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0597. Min Act: -0.1700

Data Index: 734109 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0439. Min Act: -0.1700

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 823273 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 303093 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 650098 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 1317762 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0123. Min Act: -0.1700

Data Index: 849848 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 648754 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0439. Min Act: -0.1700

Data Index: 1336610 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 1106715 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0123. Min Act: -0.1700

Data Index: 1341325 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0439. Min Act: -0.1700

Data Index: 919205 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0123. Min Act: -0.1700

Data Index: 611030 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0123. Min Act: -0.1700

Data Index: 1132816 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0281. Min Act: -0.1700

Data Index: 1192316 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.1385. Min Range: -3.1385

Max Act: 2.9965. Min Act: -0.1700

Data Index: 1266596 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0123. Min Act: -0.1700

Data Index: 21023 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 3.1385. Min Range: -3.1385

Max Act: 3.0123. Min Act: -0.1700

Data Index: 814904 (C4 (Web Text))

Max Activating Token Index: 724