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

Dataset: Open Web Text

Neuron 206 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: 5.1383. Min Range: -5.1383

Max Act: 5.1257. Min Act: -0.1700

Data Index: 8375367 (Open Web Text)

Max Activating Token Index: 432

Text #1

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.1383. Min Act: -0.1700

Data Index: 3272057 (Open Web Text)

Max Activating Token Index: 187

Text #2

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.1182. Min Act: -0.1700

Data Index: 5515257 (Open Web Text)

Max Activating Token Index: 972

Text #3

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0921. Min Act: -0.1700

Data Index: 8345880 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0932. Min Act: -0.1700

Data Index: 4160259 (Open Web Text)

Max Activating Token Index: 448

Text #5

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0876. Min Act: -0.1700

Data Index: 3382477 (Open Web Text)

Max Activating Token Index: 352

Text #6

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0660. Min Act: -0.1700

Data Index: 5554414 (Open Web Text)

Max Activating Token Index: 510

Text #7

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0391. Min Act: -0.1700

Data Index: 6489106 (Open Web Text)

Max Activating Token Index: 744

Text #8

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0221. Min Act: -0.1700

Data Index: 7560303 (Open Web Text)

Max Activating Token Index: 61

Text #9

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0142. Min Act: -0.1700

Data Index: 2899782 (Open Web Text)

Max Activating Token Index: 679

Text #10

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0283. Min Act: -0.1700

Data Index: 7645037 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9436. Min Act: -0.1700

Data Index: 6773252 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9686. Min Act: -0.1700

Data Index: 3462651 (Open Web Text)

Max Activating Token Index: 181

Text #13

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9812. Min Act: -0.1700

Data Index: 1665099 (Open Web Text)

Max Activating Token Index: 609

Text #14

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9887. Min Act: -0.1700

Data Index: 7568417 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 5.1383. Min Range: -5.1383

Max Act: 5.0030. Min Act: -0.1700

Data Index: 1262366 (Open Web Text)

Max Activating Token Index: 563

Text #16

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9883. Min Act: -0.1700

Data Index: 4003737 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9542. Min Act: -0.1700

Data Index: 3042630 (Open Web Text)

Max Activating Token Index: 796

Text #18

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9839. Min Act: -0.1700

Data Index: 5477013 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 5.1383. Min Range: -5.1383

Max Act: 4.9969. Min Act: -0.1700

Data Index: 3557039 (Open Web Text)

Max Activating Token Index: 527