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

Dataset: Open Web Text

Neuron 4763 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.8320. Min Act: -0.1700

Data Index: 5787513 (Open Web Text)

Max Activating Token Index: 374

Text #1

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.6445. Min Act: -0.1700

Data Index: 7957147 (Open Web Text)

Max Activating Token Index: 74

Text #2

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.5195. Min Act: -0.1700

Data Index: 358970 (Open Web Text)

Max Activating Token Index: 201

Text #3

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.5195. Min Act: -0.1700

Data Index: 5246613 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.4257. Min Act: -0.1700

Data Index: 7080276 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.3007. Min Act: -0.1700

Data Index: 944326 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.2382. Min Act: -0.1700

Data Index: 4912607 (Open Web Text)

Max Activating Token Index: 669

Text #7

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.2070. Min Act: -0.1700

Data Index: 4875055 (Open Web Text)

Max Activating Token Index: 655

Text #8

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.2070. Min Act: -0.1700

Data Index: 5036472 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.1445. Min Act: -0.1700

Data Index: 3853130 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.1445. Min Act: -0.1700

Data Index: 3631100 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.1132. Min Act: -0.1700

Data Index: 1421642 (Open Web Text)

Max Activating Token Index: 965

Text #12

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.1132. Min Act: -0.1700

Data Index: 5491502 (Open Web Text)

Max Activating Token Index: 827

Text #13

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.1445. Min Act: -0.1699

Data Index: 2027868 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.0820. Min Act: -0.1700

Data Index: 6441935 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.0820. Min Act: -0.1700

Data Index: 6312844 (Open Web Text)

Max Activating Token Index: 660

Text #16

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.0195. Min Act: -0.1700

Data Index: 7575960 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.0507. Min Act: -0.1700

Data Index: 5284429 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.0195. Min Act: -0.1700

Data Index: 5644222 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 7.8320. Min Range: -7.8320

Max Act: 7.0195. Min Act: -0.1700

Data Index: 82931 (Open Web Text)

Max Activating Token Index: 1004