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

Dataset: Open Web Text

Neuron 634 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: 3.3740. Min Range: -3.3740

Max Act: 3.3740. Min Act: -0.1700

Data Index: 4837928 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3655. Min Act: -0.1700

Data Index: 6432339 (Open Web Text)

Max Activating Token Index: 426

Text #2

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3417. Min Act: -0.1700

Data Index: 3347623 (Open Web Text)

Max Activating Token Index: 284

Text #3

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.3294. Min Act: -0.1700

Data Index: 5797912 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2624. Min Act: -0.1700

Data Index: 5138032 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2545. Min Act: -0.1700

Data Index: 3563069 (Open Web Text)

Max Activating Token Index: 415

Text #6

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2409. Min Act: -0.1700

Data Index: 2101629 (Open Web Text)

Max Activating Token Index: 762

Text #7

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2143. Min Act: -0.1700

Data Index: 3729206 (Open Web Text)

Max Activating Token Index: 970

Text #8

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2302. Min Act: -0.1700

Data Index: 2093126 (Open Web Text)

Max Activating Token Index: 396

Text #9

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2042. Min Act: -0.1700

Data Index: 946623 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2066. Min Act: -0.1700

Data Index: 8147547 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2408. Min Act: -0.1700

Data Index: 2093125 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1871. Min Act: -0.1700

Data Index: 6690980 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2047. Min Act: -0.1700

Data Index: 6943566 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.2108. Min Act: -0.1700

Data Index: 7942492 (Open Web Text)

Max Activating Token Index: 120

Text #15

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1829. Min Act: -0.1700

Data Index: 2856391 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1860. Min Act: -0.1700

Data Index: 4410341 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1839. Min Act: -0.1700

Data Index: 1827104 (Open Web Text)

Max Activating Token Index: 169

Text #18

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1814. Min Act: -0.1700

Data Index: 6081702 (Open Web Text)

Max Activating Token Index: 651

Text #19

Max Range: 3.3740. Min Range: -3.3740

Max Act: 3.1960. Min Act: -0.1700

Data Index: 6104648 (Open Web Text)

Max Activating Token Index: 15