Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2043 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.8827. Min Act: -0.1666

Data Index: 1457463 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.8165. Min Act: -0.1700

Data Index: 1276805 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7844. Min Act: -0.1666

Data Index: 1491250 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.8053. Min Act: -0.1666

Data Index: 1653404 (Python Code)

Max Activating Token Index: 532

Text #4

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7884. Min Act: -0.1694

Data Index: 746752 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7982. Min Act: -0.1666

Data Index: 1390097 (Python Code)

Max Activating Token Index: 808

Text #6

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7624. Min Act: -0.1700

Data Index: 262008 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7746. Min Act: -0.1666

Data Index: 1282251 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7596. Min Act: -0.1700

Data Index: 1649084 (Python Code)

Max Activating Token Index: 785

Text #9

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7570. Min Act: -0.1694

Data Index: 1352302 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7267. Min Act: -0.1690

Data Index: 608764 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7153. Min Act: -0.1666

Data Index: 1444382 (Python Code)

Max Activating Token Index: 912

Text #12

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7189. Min Act: -0.1699

Data Index: 1353384 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7285. Min Act: -0.1698

Data Index: 1325428 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.6982. Min Act: -0.1700

Data Index: 1470622 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.7068. Min Act: -0.1700

Data Index: 1571004 (Python Code)

Max Activating Token Index: 682

Text #16

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.6834. Min Act: -0.1699

Data Index: 1410411 (Python Code)

Max Activating Token Index: 854

Text #17

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.6487. Min Act: -0.1666

Data Index: 1570095 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.6590. Min Act: -0.1666

Data Index: 1522444 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 3.8827. Min Range: -3.8827

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1605799 (Python Code)

Max Activating Token Index: 30