Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1622 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.1870. Min Range: -4.1870

Max Act: 4.1870. Min Act: -0.1700

Data Index: 477147 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 4.1870. Min Range: -4.1870

Max Act: 4.0620. Min Act: -0.1700

Data Index: 1086936 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8744. Min Act: -0.1700

Data Index: 937780 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8744. Min Act: -0.1700

Data Index: 663860 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 160848 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 1267590 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 184000 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 55806 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 1350339 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 181628 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 134074 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8431. Min Act: -0.1700

Data Index: 1119837 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8118. Min Act: -0.1700

Data Index: 779117 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8118. Min Act: -0.1700

Data Index: 473801 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8118. Min Act: -0.1700

Data Index: 259895 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.8118. Min Act: -0.1700

Data Index: 95651 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.7806. Min Act: -0.1700

Data Index: 1271997 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.7806. Min Act: -0.1700

Data Index: 1329089 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.7806. Min Act: -0.1700

Data Index: 330157 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 4.1870. Min Range: -4.1870

Max Act: 3.7806. Min Act: -0.1700

Data Index: 46733 (C4 (Web Text))

Max Activating Token Index: 687