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

Dataset: Open Web Text

Neuron 982 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: 3.2592. Min Range: -3.2592

Max Act: 3.2592. Min Act: -0.1700

Data Index: 2817183 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.2172. Min Act: -0.1700

Data Index: 1401040 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.2002. Min Act: -0.1700

Data Index: 5040861 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.2034. Min Act: -0.1700

Data Index: 4720408 (Open Web Text)

Max Activating Token Index: 291

Text #4

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1861. Min Act: -0.1700

Data Index: 7689209 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1827. Min Act: -0.1700

Data Index: 404519 (Open Web Text)

Max Activating Token Index: 310

Text #6

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.2039. Min Act: -0.1700

Data Index: 2714251 (Open Web Text)

Max Activating Token Index: 373

Text #7

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1731. Min Act: -0.1700

Data Index: 5615046 (Open Web Text)

Max Activating Token Index: 286

Text #8

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1712. Min Act: -0.1700

Data Index: 4805882 (Open Web Text)

Max Activating Token Index: 271

Text #9

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1700. Min Act: -0.1700

Data Index: 1501056 (Open Web Text)

Max Activating Token Index: 404

Text #10

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1719. Min Act: -0.1700

Data Index: 4664236 (Open Web Text)

Max Activating Token Index: 397

Text #11

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1613. Min Act: -0.1700

Data Index: 8618789 (Open Web Text)

Max Activating Token Index: 277

Text #12

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1558. Min Act: -0.1700

Data Index: 3704339 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1607. Min Act: -0.1700

Data Index: 6486335 (Open Web Text)

Max Activating Token Index: 187

Text #14

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1620. Min Act: -0.1700

Data Index: 534359 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1598. Min Act: -0.1700

Data Index: 7770576 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1376. Min Act: -0.1700

Data Index: 4905530 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1487. Min Act: -0.1700

Data Index: 8287103 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1444. Min Act: -0.1700

Data Index: 6009380 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 3.2592. Min Range: -3.2592

Max Act: 3.1471. Min Act: -0.1700

Data Index: 1833105 (Open Web Text)

Max Activating Token Index: 642