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

Dataset: Open Web Text

Neuron 2441 in Layer 5

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: 3.6084. Min Range: -3.6084

Max Act: 3.6084. Min Act: -0.1700

Data Index: 1252110 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2730. Min Act: -0.1700

Data Index: 3118028 (Open Web Text)

Max Activating Token Index: 394

Text #2

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2553. Min Act: -0.1700

Data Index: 7974452 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2384. Min Act: -0.1700

Data Index: 6812741 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2358. Min Act: -0.1700

Data Index: 1803459 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2385. Min Act: -0.1700

Data Index: 361485 (Open Web Text)

Max Activating Token Index: 127

Text #6

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2341. Min Act: -0.1700

Data Index: 755907 (Open Web Text)

Max Activating Token Index: 741

Text #7

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2233. Min Act: -0.1700

Data Index: 6157588 (Open Web Text)

Max Activating Token Index: 357

Text #8

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2013. Min Act: -0.1700

Data Index: 5589434 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2285. Min Act: -0.1700

Data Index: 222322 (Open Web Text)

Max Activating Token Index: 225

Text #10

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2089. Min Act: -0.1700

Data Index: 5524309 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1937. Min Act: -0.1700

Data Index: 6799306 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1863. Min Act: -0.1700

Data Index: 4388351 (Open Web Text)

Max Activating Token Index: 526

Text #13

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1916. Min Act: -0.1700

Data Index: 2184748 (Open Web Text)

Max Activating Token Index: 485

Text #14

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.2146. Min Act: -0.1700

Data Index: 8581263 (Open Web Text)

Max Activating Token Index: 568

Text #15

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1797. Min Act: -0.1700

Data Index: 4271603 (Open Web Text)

Max Activating Token Index: 503

Text #16

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1871. Min Act: -0.1700

Data Index: 8474291 (Open Web Text)

Max Activating Token Index: 150

Text #17

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1913. Min Act: -0.1700

Data Index: 6407358 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1620. Min Act: -0.1700

Data Index: 7036052 (Open Web Text)

Max Activating Token Index: 486

Text #19

Max Range: 3.6084. Min Range: -3.6084

Max Act: 3.1858. Min Act: -0.1700

Data Index: 5567774 (Open Web Text)

Max Activating Token Index: 802