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

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

Neuron 279 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: 6.1894. Min Range: -6.1894

Max Act: 6.1894. Min Act: -0.1700

Data Index: 1124716 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 6.1894. Min Range: -6.1894

Max Act: 6.0956. Min Act: -0.1700

Data Index: 708149 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.9394. Min Act: -0.1700

Data Index: 440744 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.9081. Min Act: -0.1700

Data Index: 952628 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8456. Min Act: -0.1700

Data Index: 895407 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8456. Min Act: -0.1700

Data Index: 1312541 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8456. Min Act: -0.1700

Data Index: 55707 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8144. Min Act: -0.1700

Data Index: 511076 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8144. Min Act: -0.1700

Data Index: 956894 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7831. Min Act: -0.1700

Data Index: 1346186 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8144. Min Act: -0.1700

Data Index: 120465 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7519. Min Act: -0.1700

Data Index: 1256547 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7519. Min Act: -0.1700

Data Index: 626489 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7206. Min Act: -0.1700

Data Index: 1311883 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7206. Min Act: -0.1700

Data Index: 759726 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7519. Min Act: -0.1700

Data Index: 1320780 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7206. Min Act: -0.1700

Data Index: 1267916 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.8144. Min Act: -0.1700

Data Index: 28950 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.7831. Min Act: -0.1700

Data Index: 821817 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 6.1894. Min Range: -6.1894

Max Act: 5.6894. Min Act: -0.1700

Data Index: 345109 (C4 (Web Text))

Max Activating Token Index: 830