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

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

Neuron 582 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: 3.9585. Min Range: -3.9585

Max Act: 3.9272. Min Act: -0.1700

Data Index: 1093804 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.9585. Min Act: -0.1700

Data Index: 1270795 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.9272. Min Act: -0.1700

Data Index: 2651 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.8021. Min Act: -0.1700

Data Index: 1093124 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.8021. Min Act: -0.1700

Data Index: 167181 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.8021. Min Act: -0.1700

Data Index: 942261 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.8021. Min Act: -0.1700

Data Index: 393624 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 635343 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.8021. Min Act: -0.1700

Data Index: 824231 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 313886 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 959437 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 265391 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 926361 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 624468 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 1356544 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7708. Min Act: -0.1700

Data Index: 1240646 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7082. Min Act: -0.1700

Data Index: 145569 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7395. Min Act: -0.1700

Data Index: 947208 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7395. Min Act: -0.1700

Data Index: 554429 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 3.9585. Min Range: -3.9585

Max Act: 3.7395. Min Act: -0.1700

Data Index: 495675 (C4 (Web Text))

Max Activating Token Index: 389