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

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

Neuron 1231 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.5355. Min Act: -0.1700

Data Index: 368012 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.5355. Min Act: -0.1700

Data Index: 975648 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.5041. Min Act: -0.1700

Data Index: 266176 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.5041. Min Act: -0.1700

Data Index: 1142569 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.5041. Min Act: -0.1700

Data Index: 294410 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4728. Min Act: -0.1700

Data Index: 429476 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4414. Min Act: -0.1700

Data Index: 253985 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4414. Min Act: -0.1700

Data Index: 409913 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4414. Min Act: -0.1700

Data Index: 621850 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4101. Min Act: -0.1700

Data Index: 924901 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4101. Min Act: -0.1700

Data Index: 1189778 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4101. Min Act: -0.1700

Data Index: 234159 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4414. Min Act: -0.1700

Data Index: 573849 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4414. Min Act: -0.1700

Data Index: 315781 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.4101. Min Act: -0.1700

Data Index: 853012 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1004949 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.3787. Min Act: -0.1700

Data Index: 912323 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.3787. Min Act: -0.1700

Data Index: 210421 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.3473. Min Act: -0.1700

Data Index: 1053508 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 3.5355. Min Range: -3.5355

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1146687 (C4 (Web Text))

Max Activating Token Index: 385