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

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

Neuron 909 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: 3.6704. Min Range: -3.6704

Max Act: 3.6704. Min Act: -0.1700

Data Index: 1213132 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.5765. Min Act: -0.1700

Data Index: 993718 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.5921. Min Act: -0.1700

Data Index: 617865 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.5608. Min Act: -0.1700

Data Index: 913739 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.5138. Min Act: -0.1700

Data Index: 1066464 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.5295. Min Act: -0.1700

Data Index: 63509 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.5138. Min Act: -0.1700

Data Index: 246538 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4825. Min Act: -0.1700

Data Index: 443035 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4511. Min Act: -0.1700

Data Index: 1305288 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4668. Min Act: -0.1700

Data Index: 389875 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4511. Min Act: -0.1700

Data Index: 262687 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4511. Min Act: -0.1700

Data Index: 650727 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4511. Min Act: -0.1700

Data Index: 547961 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4668. Min Act: -0.1700

Data Index: 859864 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4355. Min Act: -0.1700

Data Index: 882974 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4355. Min Act: -0.1700

Data Index: 75569 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4355. Min Act: -0.1700

Data Index: 128594 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4041. Min Act: -0.1700

Data Index: 946673 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4198. Min Act: -0.1700

Data Index: 1176366 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 3.6704. Min Range: -3.6704

Max Act: 3.4198. Min Act: -0.1700

Data Index: 120750 (C4 (Web Text))

Max Activating Token Index: 77