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

Dataset: Open Web Text

Neuron 845 in Layer 34

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.8320. Min Act: -0.1700

Data Index: 2074695 (Open Web Text)

Max Activating Token Index: 253

Text #1

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.7070. Min Act: -0.1700

Data Index: 5495111 (Open Web Text)

Max Activating Token Index: 201

Text #2

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.5820. Min Act: -0.1700

Data Index: 3878111 (Open Web Text)

Max Activating Token Index: 222

Text #3

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.6445. Min Act: -0.1700

Data Index: 2874143 (Open Web Text)

Max Activating Token Index: 428

Text #4

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.5820. Min Act: -0.1700

Data Index: 5393553 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.5820. Min Act: -0.1700

Data Index: 7527810 (Open Web Text)

Max Activating Token Index: 895

Text #6

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.5195. Min Act: -0.1700

Data Index: 8681607 (Open Web Text)

Max Activating Token Index: 345

Text #7

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.3945. Min Act: -0.1700

Data Index: 2587869 (Open Web Text)

Max Activating Token Index: 732

Text #8

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.3945. Min Act: -0.1700

Data Index: 7482317 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.3320. Min Act: -0.1700

Data Index: 2222150 (Open Web Text)

Max Activating Token Index: 315

Text #10

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.3320. Min Act: -0.1700

Data Index: 4783577 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.3320. Min Act: -0.1700

Data Index: 7769644 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.2695. Min Act: -0.1700

Data Index: 923550 (Open Web Text)

Max Activating Token Index: 984

Text #13

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.2070. Min Act: -0.1700

Data Index: 1784720 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.2070. Min Act: -0.1700

Data Index: 6155864 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.2070. Min Act: -0.1700

Data Index: 6218754 (Open Web Text)

Max Activating Token Index: 467

Text #16

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.2070. Min Act: -0.1700

Data Index: 5044645 (Open Web Text)

Max Activating Token Index: 481

Text #17

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.1445. Min Act: -0.1700

Data Index: 2973084 (Open Web Text)

Max Activating Token Index: 846

Text #18

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.1445. Min Act: -0.1700

Data Index: 404356 (Open Web Text)

Max Activating Token Index: 964

Text #19

Max Range: 8.8320. Min Range: -8.8320

Max Act: 8.1445. Min Act: -0.1700

Data Index: 4519999 (Open Web Text)

Max Activating Token Index: 945