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

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

Neuron 1062 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0681. Min Range: -6.0681

Max Act: 6.0681. Min Act: -0.1700

Data Index: 38624 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 6.0681. Min Range: -6.0681

Max Act: 6.0056. Min Act: -0.1700

Data Index: 427401 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.9744. Min Act: -0.1700

Data Index: 1189887 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.9119. Min Act: -0.1700

Data Index: 301949 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.9119. Min Act: -0.1700

Data Index: 1275201 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8806. Min Act: -0.1700

Data Index: 83360 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8494. Min Act: -0.1700

Data Index: 790342 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8181. Min Act: -0.1700

Data Index: 216306 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7869. Min Act: -0.1700

Data Index: 569525 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8181. Min Act: -0.1700

Data Index: 1142864 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8181. Min Act: -0.1700

Data Index: 768737 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7869. Min Act: -0.1700

Data Index: 634258 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7869. Min Act: -0.1700

Data Index: 325812 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8181. Min Act: -0.1700

Data Index: 806944 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7869. Min Act: -0.1700

Data Index: 1356655 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.8181. Min Act: -0.1700

Data Index: 182687 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7869. Min Act: -0.1700

Data Index: 334294 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7869. Min Act: -0.1700

Data Index: 1225393 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7244. Min Act: -0.1700

Data Index: 1091064 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 6.0681. Min Range: -6.0681

Max Act: 5.7556. Min Act: -0.1700

Data Index: 741195 (C4 (Web Text))

Max Activating Token Index: 897