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

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

Neuron 1279 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.8512. Min Act: -0.1700

Data Index: 958962 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.8512. Min Act: -0.1700

Data Index: 255384 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.6012. Min Act: -0.1700

Data Index: 48477 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.4762. Min Act: -0.1700

Data Index: 918186 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.6012. Min Act: -0.1700

Data Index: 325099 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.6012. Min Act: -0.1700

Data Index: 444103 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5387. Min Act: -0.1700

Data Index: 761923 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5387. Min Act: -0.1700

Data Index: 1136146 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5700. Min Act: -0.1700

Data Index: 62325 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5387. Min Act: -0.1700

Data Index: 1356996 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5700. Min Act: -0.1700

Data Index: 1275598 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5387. Min Act: -0.1700

Data Index: 238639 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.6325. Min Act: -0.1700

Data Index: 881056 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.3825. Min Act: -0.1700

Data Index: 53684 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.4762. Min Act: -0.1700

Data Index: 907484 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.4450. Min Act: -0.1700

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.5700. Min Act: -0.1700

Data Index: 767234 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.4762. Min Act: -0.1700

Data Index: 267710 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.4762. Min Act: -0.1700

Data Index: 739553 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 7.8512. Min Range: -7.8512

Max Act: 7.3200. Min Act: -0.1700

Data Index: 666806 (C4 (Web Text))

Max Activating Token Index: 436