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

Dataset: Open Web Text

Neuron 2882 in Layer 6

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: 6.8122. Min Range: -6.8122

Max Act: 6.8122. Min Act: -0.1700

Data Index: 5162373 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.6573. Min Act: -0.1700

Data Index: 1128139 (Open Web Text)

Max Activating Token Index: 408

Text #2

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.7143. Min Act: -0.1700

Data Index: 2105555 (Open Web Text)

Max Activating Token Index: 202

Text #3

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.6702. Min Act: -0.1700

Data Index: 6221865 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.6124. Min Act: -0.1700

Data Index: 6307706 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.5571. Min Act: -0.1700

Data Index: 3541554 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.5061. Min Act: -0.1700

Data Index: 2992595 (Open Web Text)

Max Activating Token Index: 310

Text #7

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.4676. Min Act: -0.1700

Data Index: 1868868 (Open Web Text)

Max Activating Token Index: 988

Text #8

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.4221. Min Act: -0.1700

Data Index: 4124212 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.3374. Min Act: -0.1700

Data Index: 674100 (Open Web Text)

Max Activating Token Index: 788

Text #10

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.2960. Min Act: -0.1700

Data Index: 8515543 (Open Web Text)

Max Activating Token Index: 672

Text #11

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.2347. Min Act: -0.1700

Data Index: 6853350 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.2383. Min Act: -0.1700

Data Index: 6877284 (Open Web Text)

Max Activating Token Index: 819

Text #13

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.2563. Min Act: -0.1700

Data Index: 1747457 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.2534. Min Act: -0.1700

Data Index: 838170 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.1947. Min Act: -0.1700

Data Index: 4322982 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.1744. Min Act: -0.1700

Data Index: 518441 (Open Web Text)

Max Activating Token Index: 872

Text #17

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.1671. Min Act: -0.1700

Data Index: 1374159 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.1305. Min Act: -0.1700

Data Index: 1884633 (Open Web Text)

Max Activating Token Index: 475

Text #19

Max Range: 6.8122. Min Range: -6.8122

Max Act: 6.2134. Min Act: -0.1700

Data Index: 6112889 (Open Web Text)

Max Activating Token Index: 969