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

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

Neuron 678 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: 4.7792. Min Range: -4.7792

Max Act: 4.7792. Min Act: -0.1603

Data Index: 1549842 (Python Code)

Max Activating Token Index: 648

Text #1

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.6701. Min Act: -0.1700

Data Index: 1388400 (Python Code)

Max Activating Token Index: 877

Text #2

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.6182. Min Act: -0.1700

Data Index: 1156656 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.5872. Min Act: -0.1700

Data Index: 254566 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.5774. Min Act: -0.1669

Data Index: 1633727 (Python Code)

Max Activating Token Index: 225

Text #5

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.5744. Min Act: -0.1699

Data Index: 1444433 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.5221. Min Act: -0.1700

Data Index: 1560686 (Python Code)

Max Activating Token Index: 272

Text #7

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.5152. Min Act: -0.1700

Data Index: 1450793 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.5098. Min Act: -0.1700

Data Index: 1555764 (Python Code)

Max Activating Token Index: 440

Text #9

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.4973. Min Act: -0.1700

Data Index: 1374878 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.4533. Min Act: -0.1700

Data Index: 1625845 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.4073. Min Act: -0.1700

Data Index: 1418351 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3989. Min Act: -0.1695

Data Index: 1298844 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3934. Min Act: -0.1700

Data Index: 1460081 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3911. Min Act: -0.1699

Data Index: 1509317 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.4172. Min Act: -0.1697

Data Index: 1495796 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3800. Min Act: -0.1200

Data Index: 1417257 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3738. Min Act: -0.1700

Data Index: 1454253 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3433. Min Act: -0.1700

Data Index: 1603627 (Python Code)

Max Activating Token Index: 249

Text #19

Max Range: 4.7792. Min Range: -4.7792

Max Act: 4.3009. Min Act: -0.1700

Data Index: 434560 (C4 (Web Text))

Max Activating Token Index: 106