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

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

Neuron 1083 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.7622. Min Act: -0.1700

Data Index: 376669 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.4333. Min Act: -0.1700

Data Index: 1086455 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.4333. Min Act: -0.1700

Data Index: 89547 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.4177. Min Act: -0.1700

Data Index: 286607 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.3863. Min Act: -0.1700

Data Index: 1293373 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.4177. Min Act: -0.1700

Data Index: 893115 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.3706. Min Act: -0.1700

Data Index: 365558 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.3235. Min Act: -0.1700

Data Index: 1169017 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.3392. Min Act: -0.1700

Data Index: 216953 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2921. Min Act: -0.1700

Data Index: 421010 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.3549. Min Act: -0.1700

Data Index: 968077 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2921. Min Act: -0.1700

Data Index: 760737 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2921. Min Act: -0.1700

Data Index: 1051167 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2764. Min Act: -0.1700

Data Index: 981341 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.3078. Min Act: -0.1700

Data Index: 71501 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2921. Min Act: -0.1700

Data Index: 307409 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2607. Min Act: -0.1700

Data Index: 51648 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2921. Min Act: -0.1700

Data Index: 635982 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2293. Min Act: -0.1700

Data Index: 301667 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 3.7622. Min Range: -3.7622

Max Act: 3.2293. Min Act: -0.1700

Data Index: 235015 (C4 (Web Text))

Max Activating Token Index: 774