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

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

Neuron 1976 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: 3.9626. Min Range: -3.9626

Max Act: 3.9626. Min Act: -0.1700

Data Index: 672930 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.9157. Min Act: -0.1700

Data Index: 1243945 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.8063. Min Act: -0.1700

Data Index: 250315 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7906. Min Act: -0.1700

Data Index: 967990 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7906. Min Act: -0.1700

Data Index: 388536 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7437. Min Act: -0.1700

Data Index: 872806 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7281. Min Act: -0.1700

Data Index: 1349095 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7437. Min Act: -0.1700

Data Index: 1080344 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7594. Min Act: -0.1700

Data Index: 947195 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7281. Min Act: -0.1700

Data Index: 226383 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6968. Min Act: -0.1700

Data Index: 837370 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7124. Min Act: -0.1700

Data Index: 1300990 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7281. Min Act: -0.1700

Data Index: 1116458 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7281. Min Act: -0.1700

Data Index: 725168 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6811. Min Act: -0.1700

Data Index: 123292 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6968. Min Act: -0.1700

Data Index: 590679 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6655. Min Act: -0.1700

Data Index: 31553 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6811. Min Act: -0.1700

Data Index: 1236293 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.6655. Min Act: -0.1700

Data Index: 747031 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 3.9626. Min Range: -3.9626

Max Act: 3.7281. Min Act: -0.1700

Data Index: 443836 (C4 (Web Text))

Max Activating Token Index: 383