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

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

Neuron 85 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: 6.1884. Min Range: -6.1884

Max Act: 6.1884. Min Act: -0.1700

Data Index: 748330 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1571. Min Act: -0.1700

Data Index: 45982 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1884. Min Act: -0.1700

Data Index: 761876 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 342920 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 796332 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 1309092 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 1287769 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 1115314 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 236518 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 102431 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 909150 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 131480 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 1313100 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 1071487 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 564686 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 1246982 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0946. Min Act: -0.1700

Data Index: 1107939 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 566118 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.0634. Min Act: -0.1700

Data Index: 156671 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 6.1884. Min Range: -6.1884

Max Act: 6.1259. Min Act: -0.1700

Data Index: 414897 (C4 (Web Text))

Max Activating Token Index: 683