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

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

Neuron 1510 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.4631. Min Act: -0.1700

Data Index: 1290029 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3219. Min Act: -0.1700

Data Index: 294737 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.3219. Min Act: -0.1700

Data Index: 917324 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.2276. Min Act: -0.1700

Data Index: 120120 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.2119. Min Act: -0.1700

Data Index: 710246 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1003285 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1489. Min Act: -0.1700

Data Index: 567235 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1804. Min Act: -0.1700

Data Index: 628890 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.2119. Min Act: -0.1700

Data Index: 294573 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1489. Min Act: -0.1700

Data Index: 233097 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1174. Min Act: -0.1700

Data Index: 836982 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1174. Min Act: -0.1700

Data Index: 909924 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1016. Min Act: -0.1700

Data Index: 343207 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.0859. Min Act: -0.1700

Data Index: 344135 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.1016. Min Act: -0.1700

Data Index: 1181237 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.0701. Min Act: -0.1700

Data Index: 792189 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.0701. Min Act: -0.1700

Data Index: 1125913 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.0543. Min Act: -0.1700

Data Index: 525288 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.0859. Min Act: -0.1700

Data Index: 479455 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 3.4631. Min Range: -3.4631

Max Act: 3.0701. Min Act: -0.1700

Data Index: 318366 (C4 (Web Text))

Max Activating Token Index: 789