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

Dataset: Open Web Text

Neuron 1337 in Layer 4

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: 3.3928. Min Range: -3.3928

Max Act: 3.3928. Min Act: -0.1700

Data Index: 840605 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.3541. Min Act: -0.1700

Data Index: 7930333 (Open Web Text)

Max Activating Token Index: 850

Text #2

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.3365. Min Act: -0.1700

Data Index: 1183265 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.3118. Min Act: -0.1700

Data Index: 2548131 (Open Web Text)

Max Activating Token Index: 574

Text #4

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2556. Min Act: -0.1700

Data Index: 8474496 (Open Web Text)

Max Activating Token Index: 36

Text #5

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2845. Min Act: -0.1700

Data Index: 1226999 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2778. Min Act: -0.1700

Data Index: 8175693 (Open Web Text)

Max Activating Token Index: 391

Text #7

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2724. Min Act: -0.1700

Data Index: 2197412 (Open Web Text)

Max Activating Token Index: 802

Text #8

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.3001. Min Act: -0.1700

Data Index: 4085715 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2315. Min Act: -0.1700

Data Index: 7687037 (Open Web Text)

Max Activating Token Index: 933

Text #10

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2467. Min Act: -0.1700

Data Index: 8061210 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.2225. Min Act: -0.1700

Data Index: 405487 (Open Web Text)

Max Activating Token Index: 747

Text #12

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1820. Min Act: -0.1700

Data Index: 5650065 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1913. Min Act: -0.1700

Data Index: 2603992 (Open Web Text)

Max Activating Token Index: 52

Text #14

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1984. Min Act: -0.1700

Data Index: 1633710 (Open Web Text)

Max Activating Token Index: 268

Text #15

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1773. Min Act: -0.1700

Data Index: 8206430 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1888. Min Act: -0.1700

Data Index: 2678157 (Open Web Text)

Max Activating Token Index: 331

Text #17

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1374. Min Act: -0.1700

Data Index: 3793079 (Open Web Text)

Max Activating Token Index: 1003

Text #18

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1522. Min Act: -0.1700

Data Index: 4034865 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 3.3928. Min Range: -3.3928

Max Act: 3.1135. Min Act: -0.1700

Data Index: 6391085 (Open Web Text)

Max Activating Token Index: 723