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

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

Neuron 585 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.8901. Min Act: -0.1700

Data Index: 819322 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6554. Min Act: -0.1700

Data Index: 98015 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6867. Min Act: -0.1700

Data Index: 47420 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6554. Min Act: -0.1700

Data Index: 1073776 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6241. Min Act: -0.1700

Data Index: 388124 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6554. Min Act: -0.1700

Data Index: 1168175 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6241. Min Act: -0.1700

Data Index: 968897 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6398. Min Act: -0.1700

Data Index: 267066 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6711. Min Act: -0.1700

Data Index: 35946 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6241. Min Act: -0.1700

Data Index: 239817 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6398. Min Act: -0.1700

Data Index: 281245 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5928. Min Act: -0.1700

Data Index: 932728 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6085. Min Act: -0.1700

Data Index: 1289463 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.6085. Min Act: -0.1700

Data Index: 863350 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5772. Min Act: -0.1700

Data Index: 1160489 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5615. Min Act: -0.1700

Data Index: 37743 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5772. Min Act: -0.1700

Data Index: 53920 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5928. Min Act: -0.1700

Data Index: 50074 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5772. Min Act: -0.1700

Data Index: 295557 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 3.8901. Min Range: -3.8901

Max Act: 3.5772. Min Act: -0.1700

Data Index: 124004 (C4 (Web Text))

Max Activating Token Index: 898