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

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

Neuron 297 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: 3.2763. Min Range: -3.2763

Max Act: 3.2763. Min Act: -0.1700

Data Index: 1331761 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.2449. Min Act: -0.1700

Data Index: 1142112 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.2292. Min Act: -0.1700

Data Index: 747994 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.2134. Min Act: -0.1700

Data Index: 797053 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.2134. Min Act: -0.1700

Data Index: 119103 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1977. Min Act: -0.1700

Data Index: 1203123 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 972674 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 133032 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 14934 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 474555 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 237403 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1662. Min Act: -0.1700

Data Index: 1317413 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 239832 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1820. Min Act: -0.1700

Data Index: 863034 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1662. Min Act: -0.1700

Data Index: 1040424 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1662. Min Act: -0.1700

Data Index: 418307 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1662. Min Act: -0.1700

Data Index: 524912 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1662. Min Act: -0.1700

Data Index: 139679 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1662. Min Act: -0.1700

Data Index: 737762 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 3.2763. Min Range: -3.2763

Max Act: 3.1505. Min Act: -0.1700

Data Index: 454412 (C4 (Web Text))

Max Activating Token Index: 303