Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 411 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.9709. Min Act: -0.1700

Data Index: 957323 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.7556. Min Act: -0.1700

Data Index: 561123 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.6354. Min Act: -0.1700

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.7001. Min Act: -0.1700

Data Index: 51667 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.6559. Min Act: -0.1700

Data Index: 1307889 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.5330. Min Act: -0.1700

Data Index: 742465 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.6243. Min Act: -0.1700

Data Index: 66864 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.5530. Min Act: -0.1700

Data Index: 309614 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.5928. Min Act: -0.1700

Data Index: 742431 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.5181. Min Act: -0.1700

Data Index: 1391917 (Python Code)

Max Activating Token Index: 680

Text #10

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4955. Min Act: -0.1700

Data Index: 76815 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4182. Min Act: -0.1700

Data Index: 1042678 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.5131. Min Act: -0.1700

Data Index: 1289818 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4610. Min Act: -0.1700

Data Index: 1162906 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4980. Min Act: -0.1700

Data Index: 284952 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4528. Min Act: -0.1700

Data Index: 756692 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4462. Min Act: -0.1700

Data Index: 120361 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4093. Min Act: -0.1700

Data Index: 346987 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.3869. Min Act: -0.1700

Data Index: 911217 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 8.9709. Min Range: -8.9709

Max Act: 8.4197. Min Act: -0.1700

Data Index: 1184873 (C4 (Web Text))

Max Activating Token Index: 349