Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 914 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1757. Min Range: -5.1757

Max Act: 5.1757. Min Act: -0.1700

Data Index: 739922 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 5.1757. Min Range: -5.1757

Max Act: 5.1132. Min Act: -0.1700

Data Index: 692862 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 5.1757. Min Range: -5.1757

Max Act: 5.0507. Min Act: -0.1700

Data Index: 278205 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 5.1757. Min Range: -5.1757

Max Act: 5.0507. Min Act: -0.1700

Data Index: 1292742 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 5.1757. Min Range: -5.1757

Max Act: 5.0194. Min Act: -0.1700

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.9569. Min Act: -0.1700

Data Index: 19249 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.9569. Min Act: -0.1700

Data Index: 885228 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8944. Min Act: -0.1700

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.9257. Min Act: -0.1700

Data Index: 980268 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8944. Min Act: -0.1700

Data Index: 1272594 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8632. Min Act: -0.1700

Data Index: 1240908 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8944. Min Act: -0.1700

Data Index: 1001245 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8944. Min Act: -0.1700

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8632. Min Act: -0.1700

Data Index: 1101097 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8319. Min Act: -0.1700

Data Index: 485156 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8632. Min Act: -0.1700

Data Index: 158263 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8632. Min Act: -0.1700

Data Index: 46407 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8632. Min Act: -0.1700

Data Index: 912964 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8632. Min Act: -0.1700

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 5.1757. Min Range: -5.1757

Max Act: 4.8319. Min Act: -0.1699

Data Index: 138927 (C4 (Web Text))

Max Activating Token Index: 496