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

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

Neuron 938 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9969. Min Act: -0.1700

Data Index: 1017655 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9656. Min Act: -0.1700

Data Index: 624286 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9344. Min Act: -0.1700

Data Index: 113283 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9031. Min Act: -0.1700

Data Index: 1078348 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8718. Min Act: -0.1700

Data Index: 618369 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9031. Min Act: -0.1700

Data Index: 326272 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9031. Min Act: -0.1700

Data Index: 76211 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.9031. Min Act: -0.1700

Data Index: 850374 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8406. Min Act: -0.1700

Data Index: 1243309 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.8093. Min Act: -0.1700

Data Index: 694910 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7467. Min Act: -0.1700

Data Index: 1299690 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7780. Min Act: -0.1700

Data Index: 768131 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7467. Min Act: -0.1700

Data Index: 288983 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7467. Min Act: -0.1700

Data Index: 1241732 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7154. Min Act: -0.1700

Data Index: 1205866 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7780. Min Act: -0.1700

Data Index: 356361 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7780. Min Act: -0.1700

Data Index: 145421 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7467. Min Act: -0.1700

Data Index: 168862 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7467. Min Act: -0.1700

Data Index: 781567 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 3.9969. Min Range: -3.9969

Max Act: 3.7154. Min Act: -0.1700

Data Index: 357214 (C4 (Web Text))

Max Activating Token Index: 537