Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1889 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.6365. Min Act: -0.1700

Data Index: 133460 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5425. Min Act: -0.1700

Data Index: 30354 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5425. Min Act: -0.1700

Data Index: 54640 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5112. Min Act: -0.1700

Data Index: 823874 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5112. Min Act: -0.1700

Data Index: 157798 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 573500 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 588292 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 898289 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 1002814 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4485. Min Act: -0.1700

Data Index: 1325080 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5112. Min Act: -0.1700

Data Index: 725883 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 493913 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.5112. Min Act: -0.1700

Data Index: 45584 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 239029 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 289020 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 364928 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4798. Min Act: -0.1700

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4171. Min Act: -0.1700

Data Index: 767920 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4485. Min Act: -0.1700

Data Index: 17380 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 3.6365. Min Range: -3.6365

Max Act: 3.4485. Min Act: -0.1700

Data Index: 222849 (C4 (Web Text))

Max Activating Token Index: 290