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

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

Neuron 1335 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: 3.6540. Min Range: -3.6540

Max Act: 3.6540. Min Act: -0.1700

Data Index: 1306886 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.6227. Min Act: -0.1700

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.6540. Min Act: -0.1700

Data Index: 266363 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.5914. Min Act: -0.1700

Data Index: 372800 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.5288. Min Act: -0.1700

Data Index: 1373700 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.5131. Min Act: -0.1699

Data Index: 1616503 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4818. Min Act: -0.1700

Data Index: 715484 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.5601. Min Act: -0.1700

Data Index: 336790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4974. Min Act: -0.1700

Data Index: 494183 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.5288. Min Act: -0.1700

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4661. Min Act: -0.1700

Data Index: 180020 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.5131. Min Act: -0.1700

Data Index: 1549417 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4504. Min Act: -0.1700

Data Index: 1495041 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4818. Min Act: -0.1700

Data Index: 742528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4034. Min Act: -0.1700

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4818. Min Act: -0.1700

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4818. Min Act: -0.1700

Data Index: 1302831 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.3877. Min Act: -0.1700

Data Index: 108301 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4347. Min Act: -0.1699

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 3.6540. Min Range: -3.6540

Max Act: 3.4034. Min Act: -0.1700

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 765