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

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

Neuron 1556 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: 5.5293. Min Range: -5.5293

Max Act: 5.5293. Min Act: -0.1700

Data Index: 680647 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.5293. Min Act: -0.1700

Data Index: 444228 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.4043. Min Act: -0.1700

Data Index: 139920 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.4668. Min Act: -0.1700

Data Index: 898160 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3731. Min Act: -0.1700

Data Index: 112691 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.4356. Min Act: -0.1700

Data Index: 1008996 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3418. Min Act: -0.1700

Data Index: 229296 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3731. Min Act: -0.1700

Data Index: 1172134 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.4356. Min Act: -0.1700

Data Index: 494101 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.5293. Min Act: -0.1700

Data Index: 1220455 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3418. Min Act: -0.1700

Data Index: 110514 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3731. Min Act: -0.1700

Data Index: 164345 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.2793. Min Act: -0.1700

Data Index: 759380 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3106. Min Act: -0.1700

Data Index: 772897 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3418. Min Act: -0.1700

Data Index: 672991 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3731. Min Act: -0.1700

Data Index: 147898 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3731. Min Act: -0.1700

Data Index: 257895 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3731. Min Act: -0.1700

Data Index: 350783 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.3418. Min Act: -0.1700

Data Index: 1071083 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 5.5293. Min Range: -5.5293

Max Act: 5.4043. Min Act: -0.1700

Data Index: 1037851 (C4 (Web Text))

Max Activating Token Index: 487