Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 907 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.9355. Min Act: -0.1700

Data Index: 506633 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.8417. Min Act: -0.1700

Data Index: 389418 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.8730. Min Act: -0.1700

Data Index: 204447 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.8730. Min Act: -0.1700

Data Index: 887842 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.7166. Min Act: -0.1700

Data Index: 811386 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.7166. Min Act: -0.1700

Data Index: 665684 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6540. Min Act: -0.1700

Data Index: 358687 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6540. Min Act: -0.1700

Data Index: 575852 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6853. Min Act: -0.1700

Data Index: 1005802 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6540. Min Act: -0.1700

Data Index: 1218089 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6540. Min Act: -0.1700

Data Index: 880770 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6540. Min Act: -0.1700

Data Index: 775856 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.5913. Min Act: -0.1700

Data Index: 1192760 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6227. Min Act: -0.1700

Data Index: 655174 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6227. Min Act: -0.1700

Data Index: 864922 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.5913. Min Act: -0.1700

Data Index: 71811 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.5913. Min Act: -0.1700

Data Index: 857255 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.5600. Min Act: -0.1700

Data Index: 535665 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.5287. Min Act: -0.1700

Data Index: 1179084 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 3.9355. Min Range: -3.9355

Max Act: 3.6227. Min Act: -0.1700

Data Index: 594687 (C4 (Web Text))

Max Activating Token Index: 430