Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 273 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.8259. Min Act: -0.1700

Data Index: 810437 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.6851. Min Act: -0.1700

Data Index: 520161 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.5286. Min Act: -0.1700

Data Index: 341276 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.5834. Min Act: -0.1700

Data Index: 1343057 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.5912. Min Act: -0.1700

Data Index: 608604 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.5207. Min Act: -0.1700

Data Index: 481986 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4972. Min Act: -0.1700

Data Index: 407798 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4424. Min Act: -0.1700

Data Index: 925928 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4659. Min Act: -0.1700

Data Index: 587212 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4345. Min Act: -0.1700

Data Index: 16645 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4737. Min Act: -0.1700

Data Index: 337587 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4110. Min Act: -0.1700

Data Index: 297847 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4424. Min Act: -0.1700

Data Index: 452367 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.3953. Min Act: -0.1700

Data Index: 1297735 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4032. Min Act: -0.1700

Data Index: 611488 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4188. Min Act: -0.1700

Data Index: 983379 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.3953. Min Act: -0.1700

Data Index: 941209 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4424. Min Act: -0.1700

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.4345. Min Act: -0.1700

Data Index: 1356709 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 3.8259. Min Range: -3.8259

Max Act: 3.3718. Min Act: -0.1700

Data Index: 249186 (C4 (Web Text))

Max Activating Token Index: 181