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

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

Neuron 384 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: 5.0265. Min Range: -5.0265

Max Act: 5.0265. Min Act: -0.1700

Data Index: 231269 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.8859. Min Act: -0.1699

Data Index: 367983 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.8546. Min Act: -0.1700

Data Index: 981654 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.8390. Min Act: -0.1700

Data Index: 1297457 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.8546. Min Act: -0.1700

Data Index: 1322655 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7765. Min Act: -0.1700

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7453. Min Act: -0.1700

Data Index: 104415 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7296. Min Act: -0.1700

Data Index: 1118242 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7609. Min Act: -0.1700

Data Index: 745357 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6984. Min Act: -0.1700

Data Index: 797944 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7453. Min Act: -0.1700

Data Index: 558446 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7140. Min Act: -0.1700

Data Index: 616301 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6828. Min Act: -0.1700

Data Index: 52360 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6984. Min Act: -0.1700

Data Index: 451443 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6828. Min Act: -0.1700

Data Index: 214998 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.7140. Min Act: -0.1700

Data Index: 718079 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6984. Min Act: -0.1700

Data Index: 280522 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6671. Min Act: -0.1700

Data Index: 229183 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6671. Min Act: -0.1699

Data Index: 1179825 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 5.0265. Min Range: -5.0265

Max Act: 4.6828. Min Act: -0.1700

Data Index: 842734 (C4 (Web Text))

Max Activating Token Index: 36