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

Dataset: Open Web Text

Neuron 440 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: 4.4365. Min Range: -4.4365

Max Act: 4.4365. Min Act: -0.1700

Data Index: 25031 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.3176. Min Act: -0.1700

Data Index: 3398779 (Open Web Text)

Max Activating Token Index: 681

Text #2

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.3102. Min Act: -0.1700

Data Index: 4829889 (Open Web Text)

Max Activating Token Index: 727

Text #3

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.2342. Min Act: -0.1700

Data Index: 4648319 (Open Web Text)

Max Activating Token Index: 386

Text #4

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.2020. Min Act: -0.1700

Data Index: 8037664 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.1514. Min Act: -0.1700

Data Index: 7926547 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.1470. Min Act: -0.1700

Data Index: 7742620 (Open Web Text)

Max Activating Token Index: 394

Text #7

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0904. Min Act: -0.1700

Data Index: 563505 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0787. Min Act: -0.1700

Data Index: 3398778 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0387. Min Act: -0.1700

Data Index: 4419581 (Open Web Text)

Max Activating Token Index: 819

Text #10

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0329. Min Act: -0.1700

Data Index: 7742619 (Open Web Text)

Max Activating Token Index: 266

Text #11

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0189. Min Act: -0.1700

Data Index: 1960202 (Open Web Text)

Max Activating Token Index: 395

Text #12

Max Range: 4.4365. Min Range: -4.4365

Max Act: 3.9937. Min Act: -0.1700

Data Index: 4477748 (Open Web Text)

Max Activating Token Index: 667

Text #13

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0157. Min Act: -0.1700

Data Index: 4607981 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0115. Min Act: -0.1700

Data Index: 3786190 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 4.4365. Min Range: -4.4365

Max Act: 4.0187. Min Act: -0.1700

Data Index: 3513546 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 4.4365. Min Range: -4.4365

Max Act: 3.9645. Min Act: -0.1700

Data Index: 4477749 (Open Web Text)

Max Activating Token Index: 675

Text #17

Max Range: 4.4365. Min Range: -4.4365

Max Act: 3.9727. Min Act: -0.1700

Data Index: 5184905 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 4.4365. Min Range: -4.4365

Max Act: 3.9474. Min Act: -0.1700

Data Index: 7846798 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 4.4365. Min Range: -4.4365

Max Act: 3.9276. Min Act: -0.1700

Data Index: 5006144 (Open Web Text)

Max Activating Token Index: 698