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

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

Neuron 1982 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: 4.1822. Min Range: -4.1822

Max Act: 4.1822. Min Act: -0.1700

Data Index: 276074 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.1213. Min Act: -0.1700

Data Index: 186653 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.1671. Min Act: -0.1700

Data Index: 73956 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.1234. Min Act: -0.1700

Data Index: 1072559 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0578. Min Act: -0.1700

Data Index: 1366906 (Python Code)

Max Activating Token Index: 550

Text #5

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0689. Min Act: -0.1700

Data Index: 131986 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0585. Min Act: -0.1700

Data Index: 183073 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0329. Min Act: -0.1700

Data Index: 1362118 (Python Code)

Max Activating Token Index: 182

Text #8

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0550. Min Act: -0.1700

Data Index: 256643 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0528. Min Act: -0.1700

Data Index: 1130148 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0814. Min Act: -0.1700

Data Index: 182961 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0567. Min Act: -0.1700

Data Index: 727712 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0106. Min Act: -0.1700

Data Index: 1301367 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0318. Min Act: -0.1700

Data Index: 761155 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0474. Min Act: -0.1700

Data Index: 567502 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 4.1822. Min Range: -4.1822

Max Act: 4.0021. Min Act: -0.1700

Data Index: 606251 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 4.1822. Min Range: -4.1822

Max Act: 3.9436. Min Act: -0.1700

Data Index: 931410 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 4.1822. Min Range: -4.1822

Max Act: 3.9158. Min Act: -0.1700

Data Index: 367982 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 4.1822. Min Range: -4.1822

Max Act: 3.9716. Min Act: -0.1700

Data Index: 1164601 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 4.1822. Min Range: -4.1822

Max Act: 3.9923. Min Act: -0.1700

Data Index: 1051889 (C4 (Web Text))

Max Activating Token Index: 789