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

Dataset: Open Web Text

Neuron 2795 in Layer 1

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: 6.3987. Min Range: -6.3987

Max Act: 6.3987. Min Act: -0.1700

Data Index: 8136276 (Open Web Text)

Max Activating Token Index: 296

Text #1

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2358. Min Act: -0.1700

Data Index: 7926233 (Open Web Text)

Max Activating Token Index: 595

Text #2

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2297. Min Act: -0.1700

Data Index: 1678224 (Open Web Text)

Max Activating Token Index: 470

Text #3

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2251. Min Act: -0.1700

Data Index: 5528566 (Open Web Text)

Max Activating Token Index: 79

Text #4

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2232. Min Act: -0.1700

Data Index: 642505 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2197. Min Act: -0.1700

Data Index: 8383919 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2364. Min Act: -0.1700

Data Index: 1893583 (Open Web Text)

Max Activating Token Index: 407

Text #7

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.2123. Min Act: -0.1699

Data Index: 3638196 (Open Web Text)

Max Activating Token Index: 375

Text #8

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1875. Min Act: -0.1700

Data Index: 5461858 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1997. Min Act: -0.1698

Data Index: 6743855 (Open Web Text)

Max Activating Token Index: 559

Text #10

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1860. Min Act: -0.1700

Data Index: 479008 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1717. Min Act: -0.1700

Data Index: 5287040 (Open Web Text)

Max Activating Token Index: 249

Text #12

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1772. Min Act: -0.1700

Data Index: 2424481 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1698. Min Act: -0.1700

Data Index: 215154 (Open Web Text)

Max Activating Token Index: 697

Text #14

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1532. Min Act: -0.1700

Data Index: 2603378 (Open Web Text)

Max Activating Token Index: 791

Text #15

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1710. Min Act: -0.1700

Data Index: 6228053 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1697. Min Act: -0.1700

Data Index: 6514257 (Open Web Text)

Max Activating Token Index: 45

Text #17

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1901. Min Act: -0.1700

Data Index: 1386298 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1707. Min Act: -0.1700

Data Index: 3060378 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 6.3987. Min Range: -6.3987

Max Act: 6.1579. Min Act: -0.1700

Data Index: 7444653 (Open Web Text)

Max Activating Token Index: 523