Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1972 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.4177. Min Act: -0.1700

Data Index: 479957 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.4310. Min Act: -0.1700

Data Index: 131212 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3785. Min Act: -0.1700

Data Index: 42205 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3887. Min Act: -0.1700

Data Index: 519895 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3628. Min Act: -0.1700

Data Index: 871303 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3407. Min Act: -0.1700

Data Index: 727713 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3689. Min Act: -0.1700

Data Index: 1358950 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3741. Min Act: -0.1700

Data Index: 1190810 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3653. Min Act: -0.1700

Data Index: 639978 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3025. Min Act: -0.1700

Data Index: 1160394 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2854. Min Act: -0.1700

Data Index: 1314739 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3082. Min Act: -0.1700

Data Index: 358203 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2845. Min Act: -0.1700

Data Index: 35196 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3023. Min Act: -0.1700

Data Index: 92491 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2983. Min Act: -0.1700

Data Index: 134872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.3146. Min Act: -0.1700

Data Index: 1278013 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2980. Min Act: -0.1700

Data Index: 583138 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2597. Min Act: -0.1700

Data Index: 916543 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2729. Min Act: -0.1700

Data Index: 872902 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 3.4310. Min Range: -3.4310

Max Act: 3.2657. Min Act: -0.1700

Data Index: 636822 (C4 (Web Text))

Max Activating Token Index: 300