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

Dataset: Open Web Text

Neuron 1403 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: 5.0490. Min Range: -5.0490

Max Act: 5.0490. Min Act: -0.1700

Data Index: 3532382 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9852. Min Act: -0.1700

Data Index: 2085349 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9704. Min Act: -0.1700

Data Index: 7522224 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9641. Min Act: -0.1700

Data Index: 7556495 (Open Web Text)

Max Activating Token Index: 813

Text #4

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9455. Min Act: -0.1700

Data Index: 5443169 (Open Web Text)

Max Activating Token Index: 606

Text #5

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9819. Min Act: -0.1700

Data Index: 7202608 (Open Web Text)

Max Activating Token Index: 614

Text #6

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9328. Min Act: -0.1700

Data Index: 3565400 (Open Web Text)

Max Activating Token Index: 506

Text #7

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9433. Min Act: -0.1700

Data Index: 2539593 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9126. Min Act: -0.1700

Data Index: 7730295 (Open Web Text)

Max Activating Token Index: 726

Text #9

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9114. Min Act: -0.1700

Data Index: 3391294 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9044. Min Act: -0.1700

Data Index: 5222726 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9069. Min Act: -0.1700

Data Index: 5880886 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.8995. Min Act: -0.1700

Data Index: 6227053 (Open Web Text)

Max Activating Token Index: 846

Text #13

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9006. Min Act: -0.1700

Data Index: 7119389 (Open Web Text)

Max Activating Token Index: 681

Text #14

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.8966. Min Act: -0.1700

Data Index: 1042102 (Open Web Text)

Max Activating Token Index: 649

Text #15

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.8929. Min Act: -0.1700

Data Index: 3526089 (Open Web Text)

Max Activating Token Index: 144

Text #16

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.8794. Min Act: -0.1700

Data Index: 2606383 (Open Web Text)

Max Activating Token Index: 268

Text #17

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.9021. Min Act: -0.1700

Data Index: 1926442 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.8727. Min Act: -0.1700

Data Index: 1663697 (Open Web Text)

Max Activating Token Index: 626

Text #19

Max Range: 5.0490. Min Range: -5.0490

Max Act: 4.8890. Min Act: -0.1700

Data Index: 1104884 (Open Web Text)

Max Activating Token Index: 231