Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2702 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.8230. Min Act: -0.1700

Data Index: 3584164 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7876. Min Act: -0.1700

Data Index: 1743181 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7764. Min Act: -0.1700

Data Index: 8343605 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7456. Min Act: -0.1700

Data Index: 8599064 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7325. Min Act: -0.1700

Data Index: 2557070 (Open Web Text)

Max Activating Token Index: 309

Text #5

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7286. Min Act: -0.1700

Data Index: 4410699 (Open Web Text)

Max Activating Token Index: 234

Text #6

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7109. Min Act: -0.1700

Data Index: 2351771 (Open Web Text)

Max Activating Token Index: 460

Text #7

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6980. Min Act: -0.1700

Data Index: 2947752 (Open Web Text)

Max Activating Token Index: 85

Text #8

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6940. Min Act: -0.1700

Data Index: 8570306 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.7091. Min Act: -0.1700

Data Index: 1080030 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6812. Min Act: -0.1700

Data Index: 8737852 (Open Web Text)

Max Activating Token Index: 455

Text #11

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6707. Min Act: -0.1700

Data Index: 846691 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6785. Min Act: -0.1700

Data Index: 3829703 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6755. Min Act: -0.1700

Data Index: 7246323 (Open Web Text)

Max Activating Token Index: 838

Text #14

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6809. Min Act: -0.1700

Data Index: 7076608 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6896. Min Act: -0.1700

Data Index: 3999150 (Open Web Text)

Max Activating Token Index: 708

Text #16

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6442. Min Act: -0.1700

Data Index: 6069125 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6807. Min Act: -0.1700

Data Index: 2596543 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6486. Min Act: -0.1700

Data Index: 4941781 (Open Web Text)

Max Activating Token Index: 196

Text #19

Max Range: 3.8230. Min Range: -3.8230

Max Act: 3.6195. Min Act: -0.1700

Data Index: 2691835 (Open Web Text)

Max Activating Token Index: 823