Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1950 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.7065. Min Act: -0.1700

Data Index: 198609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.6439. Min Act: -0.1700

Data Index: 565465 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.6439. Min Act: -0.1700

Data Index: 1335956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1054318 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5970. Min Act: -0.1700

Data Index: 991065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.6126. Min Act: -0.1700

Data Index: 1307306 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5813. Min Act: -0.1700

Data Index: 44106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5656. Min Act: -0.1700

Data Index: 692025 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5500. Min Act: -0.1700

Data Index: 723390 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5343. Min Act: -0.1700

Data Index: 1340804 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5186. Min Act: -0.1700

Data Index: 1126428 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5343. Min Act: -0.1700

Data Index: 781106 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5186. Min Act: -0.1700

Data Index: 1275058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5343. Min Act: -0.1700

Data Index: 1097346 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5186. Min Act: -0.1700

Data Index: 260456 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5500. Min Act: -0.1700

Data Index: 44870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5186. Min Act: -0.1700

Data Index: 44092 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5186. Min Act: -0.1700

Data Index: 466526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.5030. Min Act: -0.1700

Data Index: 646286 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.7065. Min Range: -3.7065

Max Act: 3.4873. Min Act: -0.1700

Data Index: 559707 (C4 (Web Text))

Max Activating Token Index: 15