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

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

Neuron 1267 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.1601. Min Act: -0.1700

Data Index: 996052 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.1914. Min Act: -0.1700

Data Index: 114529 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.1289. Min Act: -0.1700

Data Index: 1018729 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0664. Min Act: -0.1700

Data Index: 748364 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0351. Min Act: -0.1700

Data Index: 243868 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.1601. Min Act: -0.1700

Data Index: 137632 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0351. Min Act: -0.1700

Data Index: 1072183 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0976. Min Act: -0.1700

Data Index: 621077 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0039. Min Act: -0.1700

Data Index: 549770 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0976. Min Act: -0.1700

Data Index: 1055593 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0976. Min Act: -0.1700

Data Index: 1230308 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0039. Min Act: -0.1700

Data Index: 43767 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0976. Min Act: -0.1700

Data Index: 701222 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0664. Min Act: -0.1700

Data Index: 1121901 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 5.1914. Min Range: -5.1914

Max Act: 4.9726. Min Act: -0.1700

Data Index: 836718 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0039. Min Act: -0.1700

Data Index: 1074364 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0351. Min Act: -0.1700

Data Index: 343959 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0039. Min Act: -0.1700

Data Index: 972456 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0039. Min Act: -0.1700

Data Index: 419625 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 5.1914. Min Range: -5.1914

Max Act: 5.0976. Min Act: -0.1700

Data Index: 891434 (C4 (Web Text))

Max Activating Token Index: 343