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

Dataset: Open Web Text

Neuron 643 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: 4.0605. Min Range: -4.0605

Max Act: 4.0605. Min Act: -0.1700

Data Index: 6010565 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9515. Min Act: -0.1700

Data Index: 294246 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9292. Min Act: -0.1700

Data Index: 3960329 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9773. Min Act: -0.1700

Data Index: 3819637 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9279. Min Act: -0.1700

Data Index: 1419039 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9389. Min Act: -0.1700

Data Index: 6184599 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9241. Min Act: -0.1700

Data Index: 3936442 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9334. Min Act: -0.1700

Data Index: 2508166 (Open Web Text)

Max Activating Token Index: 712

Text #8

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9039. Min Act: -0.1700

Data Index: 2563668 (Open Web Text)

Max Activating Token Index: 106

Text #9

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9268. Min Act: -0.1700

Data Index: 1017008 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8899. Min Act: -0.1700

Data Index: 6093264 (Open Web Text)

Max Activating Token Index: 983

Text #11

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8877. Min Act: -0.1700

Data Index: 5669368 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8851. Min Act: -0.1700

Data Index: 5307706 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9012. Min Act: -0.1700

Data Index: 853421 (Open Web Text)

Max Activating Token Index: 60

Text #14

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8834. Min Act: -0.1700

Data Index: 309977 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.9061. Min Act: -0.1700

Data Index: 2814204 (Open Web Text)

Max Activating Token Index: 310

Text #16

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8641. Min Act: -0.1700

Data Index: 5255821 (Open Web Text)

Max Activating Token Index: 633

Text #17

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8720. Min Act: -0.1700

Data Index: 5090983 (Open Web Text)

Max Activating Token Index: 385

Text #18

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8562. Min Act: -0.1700

Data Index: 1653739 (Open Web Text)

Max Activating Token Index: 396

Text #19

Max Range: 4.0605. Min Range: -4.0605

Max Act: 3.8926. Min Act: -0.1700

Data Index: 3167152 (Open Web Text)

Max Activating Token Index: 650