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

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

Neuron 1350 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.6830. Min Act: -0.1700

Data Index: 669151 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.4799. Min Act: -0.1700

Data Index: 220499 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.4330. Min Act: -0.1700

Data Index: 581140 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.3705. Min Act: -0.1700

Data Index: 330249 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.4017. Min Act: -0.1700

Data Index: 193790 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.4955. Min Act: -0.1700

Data Index: 871650 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.3861. Min Act: -0.1700

Data Index: 1211329 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.3861. Min Act: -0.1700

Data Index: 1335034 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.3392. Min Act: -0.1700

Data Index: 902930 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.3236. Min Act: -0.1700

Data Index: 1185988 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2611. Min Act: -0.1700

Data Index: 60389 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.3705. Min Act: -0.1700

Data Index: 398866 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2299. Min Act: -0.1700

Data Index: 394450 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2455. Min Act: -0.1700

Data Index: 744184 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2299. Min Act: -0.1700

Data Index: 907076 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.1986. Min Act: -0.1700

Data Index: 887091 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2142. Min Act: -0.1700

Data Index: 1342275 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2142. Min Act: -0.1700

Data Index: 566819 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.0267. Min Act: -0.1700

Data Index: 11318 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 5.6830. Min Range: -5.6830

Max Act: 5.2455. Min Act: -0.1700

Data Index: 428141 (C4 (Web Text))

Max Activating Token Index: 399