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

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

Neuron 1917 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: 4.1022. Min Range: -4.1022

Max Act: 4.1022. Min Act: -0.1700

Data Index: 1491903 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.8699. Min Act: -0.1700

Data Index: 1569466 (Python Code)

Max Activating Token Index: 922

Text #2

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.8361. Min Act: -0.1700

Data Index: 1030891 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.8334. Min Act: -0.1700

Data Index: 78993 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7876. Min Act: -0.1700

Data Index: 1582311 (Python Code)

Max Activating Token Index: 917

Text #5

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.8071. Min Act: -0.1700

Data Index: 552247 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7800. Min Act: -0.1700

Data Index: 206295 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7754. Min Act: -0.1700

Data Index: 1354628 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7905. Min Act: -0.1700

Data Index: 995571 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.8264. Min Act: -0.1700

Data Index: 1646385 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7379. Min Act: -0.1700

Data Index: 1551197 (Python Code)

Max Activating Token Index: 861

Text #11

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7208. Min Act: -0.1700

Data Index: 1516577 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7302. Min Act: -0.1700

Data Index: 1390168 (Python Code)

Max Activating Token Index: 986

Text #13

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7916. Min Act: -0.1700

Data Index: 1273788 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7355. Min Act: -0.1700

Data Index: 1412030 (Python Code)

Max Activating Token Index: 957

Text #15

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7335. Min Act: -0.1700

Data Index: 1116835 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7563. Min Act: -0.1700

Data Index: 358221 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7767. Min Act: -0.1700

Data Index: 1532963 (Python Code)

Max Activating Token Index: 713

Text #18

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.6900. Min Act: -0.1700

Data Index: 1426437 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 4.1022. Min Range: -4.1022

Max Act: 3.7207. Min Act: -0.1700

Data Index: 938936 (C4 (Web Text))

Max Activating Token Index: 841