Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 228 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1175575 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.7127. Min Act: -0.1700

Data Index: 1127577 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.7127. Min Act: -0.1700

Data Index: 339635 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6970. Min Act: -0.1700

Data Index: 525329 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6970. Min Act: -0.1700

Data Index: 1272090 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.7127. Min Act: -0.1700

Data Index: 458168 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6970. Min Act: -0.1700

Data Index: 191765 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6657. Min Act: -0.1700

Data Index: 888080 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6657. Min Act: -0.1700

Data Index: 1328873 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6657. Min Act: -0.1700

Data Index: 743632 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6657. Min Act: -0.1700

Data Index: 846504 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6501. Min Act: -0.1700

Data Index: 809413 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6344. Min Act: -0.1700

Data Index: 193401 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6188. Min Act: -0.1700

Data Index: 7155 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6188. Min Act: -0.1700

Data Index: 969986 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6031. Min Act: -0.1700

Data Index: 1091233 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6188. Min Act: -0.1700

Data Index: 16016 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6188. Min Act: -0.1700

Data Index: 146899 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6188. Min Act: -0.1700

Data Index: 297450 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 3.7127. Min Range: -3.7127

Max Act: 3.6031. Min Act: -0.1700

Data Index: 344055 (C4 (Web Text))

Max Activating Token Index: 677