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

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

Neuron 1017 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.6867. Min Act: -0.1700

Data Index: 81961 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.6554. Min Act: -0.1700

Data Index: 335891 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.6554. Min Act: -0.1700

Data Index: 837283 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.5929. Min Act: -0.1700

Data Index: 1196127 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.5304. Min Act: -0.1700

Data Index: 14856 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4992. Min Act: -0.1700

Data Index: 1307425 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.5304. Min Act: -0.1700

Data Index: 1168949 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.5304. Min Act: -0.1700

Data Index: 1349574 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4992. Min Act: -0.1700

Data Index: 947581 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4992. Min Act: -0.1700

Data Index: 312169 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4992. Min Act: -0.1700

Data Index: 959481 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4992. Min Act: -0.1700

Data Index: 1261078 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4992. Min Act: -0.1700

Data Index: 631265 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4679. Min Act: -0.1700

Data Index: 1302370 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4679. Min Act: -0.1700

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4367. Min Act: -0.1700

Data Index: 1005659 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4679. Min Act: -0.1700

Data Index: 1327029 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4367. Min Act: -0.1700

Data Index: 1177862 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.4367. Min Act: -0.1700

Data Index: 560074 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 5.6867. Min Range: -5.6867

Max Act: 5.3742. Min Act: -0.1700

Data Index: 52555 (C4 (Web Text))

Max Activating Token Index: 372