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

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

Neuron 927 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: 3.8522. Min Range: -3.8522

Max Act: 3.8522. Min Act: -0.1700

Data Index: 1351473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.7583. Min Act: -0.1700

Data Index: 767233 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6645. Min Act: -0.1700

Data Index: 446692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.7271. Min Act: -0.1700

Data Index: 78319 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6645. Min Act: -0.1700

Data Index: 1058205 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6645. Min Act: -0.1700

Data Index: 325808 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6645. Min Act: -0.1700

Data Index: 651028 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6332. Min Act: -0.1700

Data Index: 666724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6018. Min Act: -0.1700

Data Index: 271616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6332. Min Act: -0.1700

Data Index: 690998 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6332. Min Act: -0.1700

Data Index: 482402 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6332. Min Act: -0.1700

Data Index: 111402 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.5705. Min Act: -0.1700

Data Index: 1188106 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6018. Min Act: -0.1700

Data Index: 580842 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6018. Min Act: -0.1700

Data Index: 1077436 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.6018. Min Act: -0.1700

Data Index: 1354818 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.5705. Min Act: -0.1700

Data Index: 680744 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.5392. Min Act: -0.1700

Data Index: 831575 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.5705. Min Act: -0.1700

Data Index: 1176134 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 3.8522. Min Range: -3.8522

Max Act: 3.5705. Min Act: -0.1700

Data Index: 879845 (C4 (Web Text))

Max Activating Token Index: 1020