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

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

Neuron 291 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.3973. Min Act: -0.1700

Data Index: 251843 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.3345. Min Act: -0.1700

Data Index: 560918 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2874. Min Act: -0.1700

Data Index: 480770 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2874. Min Act: -0.1700

Data Index: 350539 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.3188. Min Act: -0.1700

Data Index: 490423 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2874. Min Act: -0.1700

Data Index: 925972 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.3188. Min Act: -0.1700

Data Index: 630014 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.3031. Min Act: -0.1700

Data Index: 654894 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2560. Min Act: -0.1700

Data Index: 1268036 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2717. Min Act: -0.1700

Data Index: 1207713 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2717. Min Act: -0.1700

Data Index: 241996 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2560. Min Act: -0.1700

Data Index: 1254952 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2874. Min Act: -0.1700

Data Index: 266949 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2560. Min Act: -0.1700

Data Index: 1227414 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2717. Min Act: -0.1700

Data Index: 263100 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2560. Min Act: -0.1700

Data Index: 1192501 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2245. Min Act: -0.1700

Data Index: 631812 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2402. Min Act: -0.1700

Data Index: 732687 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2402. Min Act: -0.1700

Data Index: 681805 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 3.3973. Min Range: -3.3973

Max Act: 3.2402. Min Act: -0.1700

Data Index: 420701 (C4 (Web Text))

Max Activating Token Index: 817