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

Dataset: Open Web Text

Neuron 1895 in Layer 3

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: 3.3088. Min Range: -3.3088

Max Act: 3.3088. Min Act: -0.1700

Data Index: 6482215 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.2051. Min Act: -0.1700

Data Index: 3426039 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.2168. Min Act: -0.1700

Data Index: 7651757 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1750. Min Act: -0.1700

Data Index: 1297986 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1821. Min Act: -0.1700

Data Index: 7202450 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1791. Min Act: -0.1700

Data Index: 3385942 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1958. Min Act: -0.1700

Data Index: 1194583 (Open Web Text)

Max Activating Token Index: 449

Text #7

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1533. Min Act: -0.1700

Data Index: 3873712 (Open Web Text)

Max Activating Token Index: 773

Text #8

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1544. Min Act: -0.1700

Data Index: 2778633 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1592. Min Act: -0.1700

Data Index: 6748252 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1306. Min Act: -0.1700

Data Index: 8623368 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1276. Min Act: -0.1700

Data Index: 8366136 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1276. Min Act: -0.1700

Data Index: 5065640 (Open Web Text)

Max Activating Token Index: 209

Text #13

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1478. Min Act: -0.1700

Data Index: 4529006 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1385. Min Act: -0.1700

Data Index: 2256947 (Open Web Text)

Max Activating Token Index: 238

Text #15

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1348. Min Act: -0.1700

Data Index: 1153481 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1117. Min Act: -0.1700

Data Index: 2506990 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1076. Min Act: -0.1700

Data Index: 1022005 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1035. Min Act: -0.1700

Data Index: 1889784 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 3.3088. Min Range: -3.3088

Max Act: 3.1099. Min Act: -0.1700

Data Index: 6994330 (Open Web Text)

Max Activating Token Index: 556