Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2000 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 719103 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0442. Min Act: -0.1700

Data Index: 49978 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 291099 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 342026 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 365130 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 387887 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 573793 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 656673 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 103045 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 122942 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 732840 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 775416 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 983407 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 160202 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1075248 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1095698 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1292674 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 208151 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 3.0442. Min Range: -3.0442

Max Act: 3.0126. Min Act: -0.1700

Data Index: 1320594 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.0442. Min Range: -3.0442

Max Act: 2.9809. Min Act: -0.1700

Data Index: 237201 (C4 (Web Text))

Max Activating Token Index: 4