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

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

Neuron 1576 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.6211. Min Act: -0.1700

Data Index: 770135 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.6055. Min Act: -0.1700

Data Index: 1329459 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5272. Min Act: -0.1700

Data Index: 304217 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5272. Min Act: -0.1700

Data Index: 446862 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5429. Min Act: -0.1700

Data Index: 398250 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4802. Min Act: -0.1700

Data Index: 350197 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4959. Min Act: -0.1700

Data Index: 808915 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5272. Min Act: -0.1700

Data Index: 520344 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4959. Min Act: -0.1700

Data Index: 724604 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5429. Min Act: -0.1700

Data Index: 363428 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5115. Min Act: -0.1700

Data Index: 589803 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4959. Min Act: -0.1700

Data Index: 482953 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4959. Min Act: -0.1700

Data Index: 966572 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.5115. Min Act: -0.1700

Data Index: 313719 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4802. Min Act: -0.1700

Data Index: 1330773 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4802. Min Act: -0.1700

Data Index: 662635 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4645. Min Act: -0.1700

Data Index: 1154046 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4802. Min Act: -0.1700

Data Index: 376094 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4488. Min Act: -0.1700

Data Index: 205796 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 3.6211. Min Range: -3.6211

Max Act: 3.4645. Min Act: -0.1700

Data Index: 216355 (C4 (Web Text))

Max Activating Token Index: 998