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

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

Neuron 2041 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0716. Min Range: -5.0716

Max Act: 5.0403. Min Act: -0.1700

Data Index: 250404 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 5.0716. Min Range: -5.0716

Max Act: 5.0403. Min Act: -0.1700

Data Index: 776812 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 5.0716. Min Range: -5.0716

Max Act: 5.0716. Min Act: -0.1700

Data Index: 1348162 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 5.0716. Min Range: -5.0716

Max Act: 5.0091. Min Act: -0.1700

Data Index: 366032 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9778. Min Act: -0.1700

Data Index: 256705 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 5.0716. Min Range: -5.0716

Max Act: 5.0091. Min Act: -0.1700

Data Index: 573684 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1700

Data Index: 79624 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1700

Data Index: 626014 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1700

Data Index: 921545 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 5.0716. Min Range: -5.0716

Max Act: 5.0091. Min Act: -0.1700

Data Index: 712855 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9778. Min Act: -0.1700

Data Index: 132139 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9778. Min Act: -0.1700

Data Index: 427982 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9153. Min Act: -0.1700

Data Index: 1096049 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1700

Data Index: 240709 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9778. Min Act: -0.1700

Data Index: 1253287 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1699

Data Index: 80512 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1700

Data Index: 137676 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9778. Min Act: -0.1700

Data Index: 981148 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9466. Min Act: -0.1700

Data Index: 917056 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 5.0716. Min Range: -5.0716

Max Act: 4.9153. Min Act: -0.1700

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 771