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

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

Neuron 685 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: 3.4355. Min Range: -3.4355

Max Act: 3.4355. Min Act: -0.1700

Data Index: 247492 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.4230. Min Act: -0.1700

Data Index: 1302911 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.3888. Min Act: -0.1700

Data Index: 1229886 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2832. Min Act: -0.1700

Data Index: 378574 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2289. Min Act: -0.1700

Data Index: 1636016 (Python Code)

Max Activating Token Index: 609

Text #5

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2211. Min Act: -0.1700

Data Index: 918600 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2095. Min Act: -0.1700

Data Index: 887973 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2081. Min Act: -0.1700

Data Index: 246039 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1398661 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1964. Min Act: -0.1700

Data Index: 1543949 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2171. Min Act: -0.1700

Data Index: 1500414 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1999. Min Act: -0.1700

Data Index: 1468015 (Python Code)

Max Activating Token Index: 946

Text #12

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2028. Min Act: -0.1700

Data Index: 1605314 (Python Code)

Max Activating Token Index: 878

Text #13

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1894. Min Act: -0.1700

Data Index: 1519537 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1836. Min Act: -0.1700

Data Index: 1639248 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1766. Min Act: -0.1700

Data Index: 1009321 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1780. Min Act: -0.1700

Data Index: 689592 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1949. Min Act: -0.1700

Data Index: 207273 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.2038. Min Act: -0.1700

Data Index: 825403 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 3.4355. Min Range: -3.4355

Max Act: 3.1813. Min Act: -0.1700

Data Index: 883363 (C4 (Web Text))

Max Activating Token Index: 950