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

Dataset: Open Web Text

Neuron 1970 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: 5.3069. Min Range: -5.3069

Max Act: 5.3069. Min Act: -0.1699

Data Index: 2992848 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2474. Min Act: -0.1700

Data Index: 4338522 (Open Web Text)

Max Activating Token Index: 800

Text #2

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2629. Min Act: -0.1700

Data Index: 2158279 (Open Web Text)

Max Activating Token Index: 496

Text #3

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2603. Min Act: -0.1700

Data Index: 4777543 (Open Web Text)

Max Activating Token Index: 497

Text #4

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2521. Min Act: -0.1700

Data Index: 6008099 (Open Web Text)

Max Activating Token Index: 397

Text #5

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2568. Min Act: -0.1700

Data Index: 6080042 (Open Web Text)

Max Activating Token Index: 491

Text #6

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2623. Min Act: -0.1700

Data Index: 3466038 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2640. Min Act: -0.1700

Data Index: 649464 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2505. Min Act: -0.1700

Data Index: 6204988 (Open Web Text)

Max Activating Token Index: 946

Text #9

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2228. Min Act: -0.1700

Data Index: 5699086 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2220. Min Act: -0.1700

Data Index: 6569888 (Open Web Text)

Max Activating Token Index: 459

Text #11

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2143. Min Act: -0.1700

Data Index: 8636201 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.1635. Min Act: -0.1700

Data Index: 5819525 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.1911. Min Act: -0.1700

Data Index: 3390865 (Open Web Text)

Max Activating Token Index: 709

Text #14

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2050. Min Act: -0.1700

Data Index: 5738818 (Open Web Text)

Max Activating Token Index: 364

Text #15

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2257. Min Act: -0.1700

Data Index: 7540340 (Open Web Text)

Max Activating Token Index: 622

Text #16

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.2089. Min Act: -0.1700

Data Index: 4327839 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.1893. Min Act: -0.1700

Data Index: 5719980 (Open Web Text)

Max Activating Token Index: 465

Text #18

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.1961. Min Act: -0.1700

Data Index: 6080047 (Open Web Text)

Max Activating Token Index: 186

Text #19

Max Range: 5.3069. Min Range: -5.3069

Max Act: 5.1788. Min Act: -0.1700

Data Index: 4327838 (Open Web Text)

Max Activating Token Index: 158