Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 185 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.4139. Min Act: -0.1700

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.3201. Min Act: -0.1700

Data Index: 60471 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.3201. Min Act: -0.1700

Data Index: 1337453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.3201. Min Act: -0.1700

Data Index: 1044672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.3201. Min Act: -0.1700

Data Index: 61472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.3201. Min Act: -0.1700

Data Index: 913058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1951. Min Act: -0.1700

Data Index: 644659 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1951. Min Act: -0.1700

Data Index: 1647722 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1638. Min Act: -0.1700

Data Index: 23919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1951. Min Act: -0.1700

Data Index: 583473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1638. Min Act: -0.1700

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1326. Min Act: -0.1700

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1326. Min Act: -0.1700

Data Index: 334770 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1326. Min Act: -0.1700

Data Index: 243201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1013. Min Act: -0.1700

Data Index: 702827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1326. Min Act: -0.1700

Data Index: 629332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.1013. Min Act: -0.1700

Data Index: 759431 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.0388. Min Act: -0.1700

Data Index: 1114178 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.0701. Min Act: -0.1700

Data Index: 545503 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.4139. Min Range: -4.4139

Max Act: 4.0701. Min Act: -0.1700

Data Index: 712827 (C4 (Web Text))

Max Activating Token Index: 1023