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

Dataset: Open Web Text

Neuron 1080 in Layer 3

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: 4.8711. Min Range: -4.8711

Max Act: 4.8711. Min Act: -0.1700

Data Index: 129265 (Open Web Text)

Max Activating Token Index: 506

Text #1

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.7955. Min Act: -0.1700

Data Index: 114073 (Open Web Text)

Max Activating Token Index: 525

Text #2

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.7359. Min Act: -0.1700

Data Index: 7021781 (Open Web Text)

Max Activating Token Index: 257

Text #3

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.8316. Min Act: -0.1700

Data Index: 267316 (Open Web Text)

Max Activating Token Index: 691

Text #4

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6730. Min Act: -0.1700

Data Index: 7824048 (Open Web Text)

Max Activating Token Index: 763

Text #5

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6313. Min Act: -0.1700

Data Index: 1956946 (Open Web Text)

Max Activating Token Index: 904

Text #6

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6541. Min Act: -0.1700

Data Index: 2973824 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.7317. Min Act: -0.1699

Data Index: 2634608 (Open Web Text)

Max Activating Token Index: 407

Text #8

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.7160. Min Act: -0.1699

Data Index: 5335509 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6091. Min Act: -0.1700

Data Index: 7792923 (Open Web Text)

Max Activating Token Index: 741

Text #10

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6239. Min Act: -0.1700

Data Index: 4670971 (Open Web Text)

Max Activating Token Index: 731

Text #11

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6681. Min Act: -0.1700

Data Index: 5460848 (Open Web Text)

Max Activating Token Index: 483

Text #12

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5396. Min Act: -0.1700

Data Index: 7667233 (Open Web Text)

Max Activating Token Index: 491

Text #13

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.6184. Min Act: -0.1700

Data Index: 6101685 (Open Web Text)

Max Activating Token Index: 994

Text #14

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5382. Min Act: -0.1699

Data Index: 2975468 (Open Web Text)

Max Activating Token Index: 342

Text #15

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5855. Min Act: -0.1700

Data Index: 5096490 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5824. Min Act: -0.1699

Data Index: 1644056 (Open Web Text)

Max Activating Token Index: 160

Text #17

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5317. Min Act: -0.1700

Data Index: 8531356 (Open Web Text)

Max Activating Token Index: 214

Text #18

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5830. Min Act: -0.1700

Data Index: 3536217 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 4.8711. Min Range: -4.8711

Max Act: 4.5914. Min Act: -0.1699

Data Index: 2502210 (Open Web Text)

Max Activating Token Index: 825