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

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

Neuron 37 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.8193. Min Act: -0.1700

Data Index: 152836 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.7568. Min Act: -0.1700

Data Index: 1127962 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.6631. Min Act: -0.1700

Data Index: 21863 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.7256. Min Act: -0.1700

Data Index: 914994 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.6943. Min Act: -0.1700

Data Index: 494404 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.6318. Min Act: -0.1700

Data Index: 475649 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.6631. Min Act: -0.1700

Data Index: 186800 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.4443. Min Act: -0.1700

Data Index: 1003391 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3506. Min Act: -0.1700

Data Index: 882794 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3818. Min Act: -0.1700

Data Index: 220181 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3506. Min Act: -0.1700

Data Index: 441168 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3818. Min Act: -0.1700

Data Index: 1219796 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3193. Min Act: -0.1700

Data Index: 1027012 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3506. Min Act: -0.1700

Data Index: 1016551 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3506. Min Act: -0.1700

Data Index: 3787 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.3193. Min Act: -0.1700

Data Index: 941823 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.2881. Min Act: -0.1700

Data Index: 889314 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.2881. Min Act: -0.1700

Data Index: 504407 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.2256. Min Act: -0.1700

Data Index: 585466 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 5.8193. Min Range: -5.8193

Max Act: 5.2568. Min Act: -0.1700

Data Index: 943971 (C4 (Web Text))

Max Activating Token Index: 330