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

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

Neuron 1140 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.3241. Min Act: -0.1700

Data Index: 1490454 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.1991. Min Act: -0.1700

Data Index: 173524 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.1991. Min Act: -0.1700

Data Index: 1518290 (Python Code)

Max Activating Token Index: 427

Text #3

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0741. Min Act: -0.1700

Data Index: 96689 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0741. Min Act: -0.1700

Data Index: 255986 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0116. Min Act: -0.1700

Data Index: 791785 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0116. Min Act: -0.1700

Data Index: 1142601 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.9491. Min Act: -0.1700

Data Index: 21026 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0116. Min Act: -0.1700

Data Index: 1268039 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0116. Min Act: -0.1699

Data Index: 1079673 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0116. Min Act: -0.1700

Data Index: 617145 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.9491. Min Act: -0.1700

Data Index: 302108 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.9491. Min Act: -0.1700

Data Index: 20711 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.9491. Min Act: -0.1700

Data Index: 769614 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 7.3241. Min Range: -7.3241

Max Act: 7.0116. Min Act: -0.1700

Data Index: 895991 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.8866. Min Act: -0.1700

Data Index: 173341 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.8866. Min Act: -0.1700

Data Index: 1241280 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.8866. Min Act: -0.1700

Data Index: 873260 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.8866. Min Act: -0.1700

Data Index: 768699 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 7.3241. Min Range: -7.3241

Max Act: 6.8866. Min Act: -0.1700

Data Index: 327648 (C4 (Web Text))

Max Activating Token Index: 580