Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1079 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.0457. Min Range: -3.0457

Max Act: 3.0457. Min Act: -0.1700

Data Index: 473766 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 3.0457. Min Range: -3.0457

Max Act: 3.0300. Min Act: -0.1700

Data Index: 1012959 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 3.0457. Min Range: -3.0457

Max Act: 3.0457. Min Act: -0.1700

Data Index: 1188904 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9509. Min Act: -0.1700

Data Index: 243994 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9033. Min Act: -0.1700

Data Index: 259376 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9033. Min Act: -0.1700

Data Index: 52518 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9192. Min Act: -0.1700

Data Index: 1084241 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9192. Min Act: -0.1700

Data Index: 859550 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8875. Min Act: -0.1700

Data Index: 85685 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8716. Min Act: -0.1700

Data Index: 901845 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.9033. Min Act: -0.1700

Data Index: 765139 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8716. Min Act: -0.1700

Data Index: 843732 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8875. Min Act: -0.1700

Data Index: 1078029 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8716. Min Act: -0.1700

Data Index: 143047 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8557. Min Act: -0.1700

Data Index: 185874 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8716. Min Act: -0.1700

Data Index: 48333 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8557. Min Act: -0.1700

Data Index: 623921 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8557. Min Act: -0.1700

Data Index: 955323 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8398. Min Act: -0.1700

Data Index: 582273 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 3.0457. Min Range: -3.0457

Max Act: 2.8398. Min Act: -0.1700

Data Index: 190318 (C4 (Web Text))

Max Activating Token Index: 25