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

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

Neuron 6 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: 3.5041. Min Range: -3.5041

Max Act: 3.5041. Min Act: -0.1700

Data Index: 131174 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4728. Min Act: -0.1700

Data Index: 912230 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.4415. Min Act: -0.1700

Data Index: 1258378 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1314190 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3944. Min Act: -0.1700

Data Index: 441144 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3787. Min Act: -0.1700

Data Index: 685913 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1001304 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3787. Min Act: -0.1700

Data Index: 352173 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3787. Min Act: -0.1700

Data Index: 251484 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3630. Min Act: -0.1700

Data Index: 518644 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3630. Min Act: -0.1700

Data Index: 35453 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3316. Min Act: -0.1700

Data Index: 1151833 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3473. Min Act: -0.1700

Data Index: 611318 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3787. Min Act: -0.1700

Data Index: 992236 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3473. Min Act: -0.1700

Data Index: 980302 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3473. Min Act: -0.1700

Data Index: 737096 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3473. Min Act: -0.1700

Data Index: 559088 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3473. Min Act: -0.1700

Data Index: 779938 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3316. Min Act: -0.1700

Data Index: 575557 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 3.5041. Min Range: -3.5041

Max Act: 3.3473. Min Act: -0.1700

Data Index: 133602 (C4 (Web Text))

Max Activating Token Index: 972