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

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

Neuron 977 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: 3.2232. Min Range: -3.2232

Max Act: 3.2232. Min Act: -0.1700

Data Index: 446645 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1917. Min Act: -0.1700

Data Index: 609658 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1917. Min Act: -0.1700

Data Index: 1178629 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1602. Min Act: -0.1700

Data Index: 882335 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1602. Min Act: -0.1700

Data Index: 314677 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1602. Min Act: -0.1700

Data Index: 815388 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1602. Min Act: -0.1700

Data Index: 203937 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1760. Min Act: -0.1700

Data Index: 1144655 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 406303 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1169790 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 551406 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 1051479 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1602. Min Act: -0.1700

Data Index: 628946 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 336777 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 824064 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1445. Min Act: -0.1700

Data Index: 512773 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1287. Min Act: -0.1700

Data Index: 1009672 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1287. Min Act: -0.1700

Data Index: 718958 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1130. Min Act: -0.1700

Data Index: 593324 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 3.2232. Min Range: -3.2232

Max Act: 3.1130. Min Act: -0.1700

Data Index: 39264 (C4 (Web Text))

Max Activating Token Index: 1015