Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 4281 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.5335. Min Act: -0.1700

Data Index: 3798932 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.4085. Min Act: -0.1700

Data Index: 2851515 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.3460. Min Act: -0.1700

Data Index: 3661719 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.2523. Min Act: -0.1700

Data Index: 2988311 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.2210. Min Act: -0.1700

Data Index: 6458970 (Open Web Text)

Max Activating Token Index: 23

Text #5

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.2210. Min Act: -0.1700

Data Index: 2369584 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.1585. Min Act: -0.1700

Data Index: 7046541 (Open Web Text)

Max Activating Token Index: 463

Text #7

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.1898. Min Act: -0.1700

Data Index: 3104337 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.1898. Min Act: -0.1700

Data Index: 5712544 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.1273. Min Act: -0.1700

Data Index: 3446333 (Open Web Text)

Max Activating Token Index: 57

Text #10

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0960. Min Act: -0.1700

Data Index: 8610833 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0960. Min Act: -0.1700

Data Index: 1904129 (Open Web Text)

Max Activating Token Index: 637

Text #12

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0960. Min Act: -0.1700

Data Index: 320494 (Open Web Text)

Max Activating Token Index: 815

Text #13

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0960. Min Act: -0.1700

Data Index: 5282749 (Open Web Text)

Max Activating Token Index: 295

Text #14

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0648. Min Act: -0.1700

Data Index: 3457032 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0335. Min Act: -0.1700

Data Index: 7248055 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0023. Min Act: -0.1700

Data Index: 2259750 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0335. Min Act: -0.1700

Data Index: 2121461 (Open Web Text)

Max Activating Token Index: 502

Text #18

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0335. Min Act: -0.1700

Data Index: 454817 (Open Web Text)

Max Activating Token Index: 254

Text #19

Max Range: 5.5335. Min Range: -5.5335

Max Act: 5.0648. Min Act: -0.1700

Data Index: 2667187 (Open Web Text)

Max Activating Token Index: 5