Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1724 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.4850. Min Act: -0.1700

Data Index: 1282346 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.4380. Min Act: -0.1700

Data Index: 858327 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3909. Min Act: -0.1700

Data Index: 1355657 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3909. Min Act: -0.1700

Data Index: 10266 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3909. Min Act: -0.1700

Data Index: 1195673 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3596. Min Act: -0.1700

Data Index: 827838 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3596. Min Act: -0.1700

Data Index: 1228359 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3596. Min Act: -0.1700

Data Index: 231970 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3596. Min Act: -0.1700

Data Index: 986433 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3439. Min Act: -0.1700

Data Index: 296622 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3439. Min Act: -0.1700

Data Index: 380676 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1232139 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.2968. Min Act: -0.1700

Data Index: 353124 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3125. Min Act: -0.1700

Data Index: 1114187 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.2968. Min Act: -0.1700

Data Index: 740578 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.3282. Min Act: -0.1700

Data Index: 40913 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.2968. Min Act: -0.1700

Data Index: 1232452 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.2968. Min Act: -0.1700

Data Index: 1034818 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.2496. Min Act: -0.1700

Data Index: 1101413 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.4850. Min Range: -3.4850

Max Act: 3.2496. Min Act: -0.1700

Data Index: 559101 (C4 (Web Text))

Max Activating Token Index: 253