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

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

Neuron 1310 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: 3.7257. Min Range: -3.7257

Max Act: 3.7257. Min Act: -0.1700

Data Index: 133238 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.7257. Min Act: -0.1700

Data Index: 770460 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.7257. Min Act: -0.1700

Data Index: 671309 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.6631. Min Act: -0.1700

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5691. Min Act: -0.1700

Data Index: 849784 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5691. Min Act: -0.1700

Data Index: 382536 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5691. Min Act: -0.1700

Data Index: 1046807 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5378. Min Act: -0.1700

Data Index: 1137620 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5378. Min Act: -0.1700

Data Index: 1098435 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5065. Min Act: -0.1700

Data Index: 1003301 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5378. Min Act: -0.1700

Data Index: 98268 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5378. Min Act: -0.1700

Data Index: 852135 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5065. Min Act: -0.1700

Data Index: 883896 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5691. Min Act: -0.1700

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5378. Min Act: -0.1700

Data Index: 1097966 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5691. Min Act: -0.1700

Data Index: 1081560 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5691. Min Act: -0.1700

Data Index: 285400 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.4751. Min Act: -0.1700

Data Index: 368349 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5065. Min Act: -0.1700

Data Index: 925624 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 3.7257. Min Range: -3.7257

Max Act: 3.5065. Min Act: -0.1700

Data Index: 252534 (C4 (Web Text))

Max Activating Token Index: 400