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

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

Neuron 1940 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: 3.8738. Min Range: -3.8738

Max Act: 3.8738. Min Act: -0.1700

Data Index: 237692 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.8425. Min Act: -0.1700

Data Index: 511416 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.8425. Min Act: -0.1700

Data Index: 685756 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.8112. Min Act: -0.1700

Data Index: 1347081 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7799. Min Act: -0.1700

Data Index: 507766 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7486. Min Act: -0.1700

Data Index: 700809 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7799. Min Act: -0.1700

Data Index: 1101856 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 933190 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 1317604 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7486. Min Act: -0.1700

Data Index: 1309845 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 288198 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 1072207 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.6861. Min Act: -0.1700

Data Index: 1154527 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.6861. Min Act: -0.1700

Data Index: 1094892 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.6861. Min Act: -0.1700

Data Index: 459779 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 1130224 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 522174 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.7173. Min Act: -0.1700

Data Index: 631301 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.6861. Min Act: -0.1700

Data Index: 259645 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 3.8738. Min Range: -3.8738

Max Act: 3.6861. Min Act: -0.1700

Data Index: 429718 (C4 (Web Text))

Max Activating Token Index: 48