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

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

Neuron 1429 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: 5.7337. Min Range: -5.7337

Max Act: 5.7337. Min Act: -0.1700

Data Index: 17135 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.7024. Min Act: -0.1700

Data Index: 473088 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6712. Min Act: -0.1700

Data Index: 354266 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6712. Min Act: -0.1700

Data Index: 263206 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1072592 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.7024. Min Act: -0.1700

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6712. Min Act: -0.1700

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 277178 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1269177 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1348691 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 679042 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 33234 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1170119 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.5774. Min Act: -0.1700

Data Index: 1316356 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6087. Min Act: -0.1700

Data Index: 148123 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6087. Min Act: -0.1700

Data Index: 236255 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6399. Min Act: -0.1700

Data Index: 380147 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.5774. Min Act: -0.1700

Data Index: 465811 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.6087. Min Act: -0.1700

Data Index: 209375 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 5.7337. Min Range: -5.7337

Max Act: 5.5774. Min Act: -0.1700

Data Index: 737691 (C4 (Web Text))

Max Activating Token Index: 622