Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1530 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1756. Min Act: -0.1700

Data Index: 166916 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1443. Min Act: -0.1700

Data Index: 797785 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.2068. Min Act: -0.1700

Data Index: 1003901 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1756. Min Act: -0.1700

Data Index: 1076770 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1443. Min Act: -0.1700

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1131. Min Act: -0.1700

Data Index: 969249 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1131. Min Act: -0.1700

Data Index: 550901 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1131. Min Act: -0.1700

Data Index: 974563 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1131. Min Act: -0.1700

Data Index: 1324330 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.0818. Min Act: -0.1700

Data Index: 1123064 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.0506. Min Act: -0.1700

Data Index: 236140 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.0818. Min Act: -0.1700

Data Index: 17906 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.0506. Min Act: -0.1700

Data Index: 128239 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.1131. Min Act: -0.1700

Data Index: 919335 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 5.2068. Min Range: -5.2068

Max Act: 4.9881. Min Act: -0.1700

Data Index: 1185950 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.0506. Min Act: -0.1700

Data Index: 280620 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 5.2068. Min Range: -5.2068

Max Act: 5.0193. Min Act: -0.1700

Data Index: 281954 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 5.2068. Min Range: -5.2068

Max Act: 4.9568. Min Act: -0.1700

Data Index: 555193 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 5.2068. Min Range: -5.2068

Max Act: 4.9881. Min Act: -0.1700

Data Index: 1178305 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 5.2068. Min Range: -5.2068

Max Act: 4.9881. Min Act: -0.1700

Data Index: 141592 (C4 (Web Text))

Max Activating Token Index: 403