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

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

Neuron 1307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.1126. Min Act: -0.1700

Data Index: 1310540 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.0814. Min Act: -0.1700

Data Index: 555984 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.0501. Min Act: -0.1700

Data Index: 1014573 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.0814. Min Act: -0.1700

Data Index: 1349178 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.0188. Min Act: -0.1700

Data Index: 278984 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.0188. Min Act: -0.1700

Data Index: 352812 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9876. Min Act: -0.1700

Data Index: 249129 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9876. Min Act: -0.1700

Data Index: 467234 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 4.1126. Min Range: -4.1126

Max Act: 4.0188. Min Act: -0.1700

Data Index: 809429 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9876. Min Act: -0.1700

Data Index: 221855 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9563. Min Act: -0.1700

Data Index: 1119040 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9876. Min Act: -0.1700

Data Index: 245215 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9563. Min Act: -0.1700

Data Index: 351414 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9250. Min Act: -0.1700

Data Index: 64052 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9250. Min Act: -0.1700

Data Index: 1047299 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.8938. Min Act: -0.1700

Data Index: 329855 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9563. Min Act: -0.1700

Data Index: 753694 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9250. Min Act: -0.1700

Data Index: 476459 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9250. Min Act: -0.1700

Data Index: 959493 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 4.1126. Min Range: -4.1126

Max Act: 3.9250. Min Act: -0.1700

Data Index: 216042 (C4 (Web Text))

Max Activating Token Index: 320