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

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

Neuron 166 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.3343. Min Act: -0.1700

Data Index: 69856 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.2872. Min Act: -0.1700

Data Index: 1319305 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.2244. Min Act: -0.1700

Data Index: 489737 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.2558. Min Act: -0.1700

Data Index: 586123 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.2086. Min Act: -0.1700

Data Index: 289197 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.2244. Min Act: -0.1700

Data Index: 674300 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.2244. Min Act: -0.1700

Data Index: 30231 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1929. Min Act: -0.1700

Data Index: 1315016 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1929. Min Act: -0.1700

Data Index: 696941 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1929. Min Act: -0.1700

Data Index: 130452 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1929. Min Act: -0.1700

Data Index: 225309 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1772. Min Act: -0.1700

Data Index: 909945 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1772. Min Act: -0.1700

Data Index: 1573 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1614. Min Act: -0.1700

Data Index: 197290 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1299. Min Act: -0.1700

Data Index: 1207511 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1457. Min Act: -0.1700

Data Index: 1119510 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1299. Min Act: -0.1700

Data Index: 1287259 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.1142. Min Act: -0.1700

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.0984. Min Act: -0.1700

Data Index: 66402 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 3.3343. Min Range: -3.3343

Max Act: 3.0984. Min Act: -0.1700

Data Index: 314622 (C4 (Web Text))

Max Activating Token Index: 426