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

Dataset: Open Web Text

Neuron 1651 in Layer 2

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: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.1700

Data Index: 8779561 (Open Web Text)

Max Activating Token Index: 570

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2475. Min Act: -0.1698

Data Index: 4330085 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2307. Min Act: -0.1699

Data Index: 2985372 (Open Web Text)

Max Activating Token Index: 774

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2422. Min Act: -0.1700

Data Index: 7167128 (Open Web Text)

Max Activating Token Index: 613

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2245. Min Act: -0.1700

Data Index: 295001 (Open Web Text)

Max Activating Token Index: 1016

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2258. Min Act: -0.1700

Data Index: 6350498 (Open Web Text)

Max Activating Token Index: 751

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2203. Min Act: -0.1700

Data Index: 609026 (Open Web Text)

Max Activating Token Index: 978

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2130. Min Act: -0.1699

Data Index: 4398302 (Open Web Text)

Max Activating Token Index: 842

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2230. Min Act: -0.1700

Data Index: 5434019 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2054. Min Act: -0.1700

Data Index: 7992586 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1992. Min Act: -0.1700

Data Index: 5282286 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2061. Min Act: -0.1700

Data Index: 6610942 (Open Web Text)

Max Activating Token Index: 987

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1941. Min Act: -0.1700

Data Index: 153943 (Open Web Text)

Max Activating Token Index: 761

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1987. Min Act: -0.1700

Data Index: 763006 (Open Web Text)

Max Activating Token Index: 668

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1947. Min Act: -0.1700

Data Index: 553082 (Open Web Text)

Max Activating Token Index: 653

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1997. Min Act: -0.1700

Data Index: 7090974 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1873. Min Act: -0.1700

Data Index: 1296375 (Open Web Text)

Max Activating Token Index: 977

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1971. Min Act: -0.1700

Data Index: 6516942 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1877. Min Act: -0.1700

Data Index: 3474850 (Open Web Text)

Max Activating Token Index: 115

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.1847. Min Act: -0.1700

Data Index: 8116865 (Open Web Text)

Max Activating Token Index: 1009