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

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

Neuron 1408 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: 3.0263. Min Range: -3.0263

Max Act: 3.0263. Min Act: -0.1700

Data Index: 1034631 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9631. Min Act: -0.1700

Data Index: 1254528 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9472. Min Act: -0.1700

Data Index: 529855 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9314. Min Act: -0.1700

Data Index: 241927 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9314. Min Act: -0.1700

Data Index: 268345 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9314. Min Act: -0.1700

Data Index: 1274826 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9155. Min Act: -0.1700

Data Index: 375035 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.9155. Min Act: -0.1700

Data Index: 205179 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8997. Min Act: -0.1700

Data Index: 726407 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8997. Min Act: -0.1700

Data Index: 538327 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8838. Min Act: -0.1700

Data Index: 729774 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8679. Min Act: -0.1700

Data Index: 674428 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8679. Min Act: -0.1700

Data Index: 1110593 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8838. Min Act: -0.1700

Data Index: 1160345 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8520. Min Act: -0.1700

Data Index: 332569 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8362. Min Act: -0.1700

Data Index: 925240 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8520. Min Act: -0.1700

Data Index: 48782 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8520. Min Act: -0.1700

Data Index: 380491 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8202. Min Act: -0.1700

Data Index: 1071546 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 3.0263. Min Range: -3.0263

Max Act: 2.8362. Min Act: -0.1700

Data Index: 1096166 (C4 (Web Text))

Max Activating Token Index: 892