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

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

Neuron 216 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: 5.9032. Min Range: -5.9032

Max Act: 5.9032. Min Act: -0.1700

Data Index: 85312 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.8407. Min Act: -0.1700

Data Index: 611107 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.8407. Min Act: -0.1700

Data Index: 821031 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.8094. Min Act: -0.1700

Data Index: 940742 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.8407. Min Act: -0.1700

Data Index: 349627 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.7469. Min Act: -0.1700

Data Index: 1166416 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.7782. Min Act: -0.1700

Data Index: 122812 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.8094. Min Act: -0.1700

Data Index: 1234734 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.7469. Min Act: -0.1700

Data Index: 545688 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.7469. Min Act: -0.1700

Data Index: 452643 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6844. Min Act: -0.1700

Data Index: 515582 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6532. Min Act: -0.1700

Data Index: 1099072 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6844. Min Act: -0.1700

Data Index: 1149899 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6844. Min Act: -0.1700

Data Index: 1161871 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6532. Min Act: -0.1700

Data Index: 726255 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6532. Min Act: -0.1700

Data Index: 1315104 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6219. Min Act: -0.1700

Data Index: 293485 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6532. Min Act: -0.1700

Data Index: 590478 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.6532. Min Act: -0.1700

Data Index: 1135774 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 5.9032. Min Range: -5.9032

Max Act: 5.5282. Min Act: -0.1700

Data Index: 971720 (C4 (Web Text))

Max Activating Token Index: 871