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

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

Neuron 1646 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: 3.8718. Min Range: -3.8718

Max Act: 3.8718. Min Act: -0.1700

Data Index: 647643 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8093. Min Act: -0.1700

Data Index: 536189 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8406. Min Act: -0.1700

Data Index: 1311484 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7936. Min Act: -0.1700

Data Index: 1080814 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8249. Min Act: -0.1700

Data Index: 694747 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8406. Min Act: -0.1700

Data Index: 1160578 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8249. Min Act: -0.1700

Data Index: 643313 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7780. Min Act: -0.1700

Data Index: 866773 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.8093. Min Act: -0.1700

Data Index: 568685 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7936. Min Act: -0.1700

Data Index: 1252024 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7780. Min Act: -0.1700

Data Index: 1114343 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7780. Min Act: -0.1700

Data Index: 857420 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7624. Min Act: -0.1700

Data Index: 922753 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7624. Min Act: -0.1700

Data Index: 421951 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7154. Min Act: -0.1700

Data Index: 744208 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7467. Min Act: -0.1700

Data Index: 261010 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7624. Min Act: -0.1700

Data Index: 1264491 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7780. Min Act: -0.1700

Data Index: 1178593 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7624. Min Act: -0.1700

Data Index: 33028 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 3.8718. Min Range: -3.8718

Max Act: 3.7936. Min Act: -0.1700

Data Index: 861277 (C4 (Web Text))

Max Activating Token Index: 986