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

Dataset: Open Web Text

Neuron 2699 in Layer 1

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: 5.3857. Min Range: -5.3857

Max Act: 5.3857. Min Act: -0.1700

Data Index: 2349742 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.3515. Min Act: -0.1700

Data Index: 583400 (Open Web Text)

Max Activating Token Index: 376

Text #2

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.3230. Min Act: -0.1700

Data Index: 8417555 (Open Web Text)

Max Activating Token Index: 820

Text #3

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2762. Min Act: -0.1700

Data Index: 2492407 (Open Web Text)

Max Activating Token Index: 1016

Text #4

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2733. Min Act: -0.1700

Data Index: 2646132 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2360. Min Act: -0.1700

Data Index: 978180 (Open Web Text)

Max Activating Token Index: 972

Text #6

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2448. Min Act: -0.1700

Data Index: 3802818 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2281. Min Act: -0.1700

Data Index: 5981846 (Open Web Text)

Max Activating Token Index: 429

Text #8

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2518. Min Act: -0.1700

Data Index: 7707106 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2398. Min Act: -0.1700

Data Index: 1521220 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2556. Min Act: -0.1700

Data Index: 8742962 (Open Web Text)

Max Activating Token Index: 519

Text #11

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2487. Min Act: -0.1700

Data Index: 3662886 (Open Web Text)

Max Activating Token Index: 533

Text #12

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2497. Min Act: -0.1700

Data Index: 3637643 (Open Web Text)

Max Activating Token Index: 406

Text #13

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2302. Min Act: -0.1700

Data Index: 2238213 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2146. Min Act: -0.1700

Data Index: 2151622 (Open Web Text)

Max Activating Token Index: 396

Text #15

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2184. Min Act: -0.1700

Data Index: 3461978 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2194. Min Act: -0.1700

Data Index: 3143972 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2354. Min Act: -0.1700

Data Index: 3072712 (Open Web Text)

Max Activating Token Index: 743

Text #18

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2133. Min Act: -0.1700

Data Index: 3018650 (Open Web Text)

Max Activating Token Index: 998

Text #19

Max Range: 5.3857. Min Range: -5.3857

Max Act: 5.2296. Min Act: -0.1700

Data Index: 511241 (Open Web Text)

Max Activating Token Index: 219