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

Dataset: Open Web Text

Neuron 3019 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: 4.5416. Min Range: -4.5416

Max Act: 4.5416. Min Act: -0.1700

Data Index: 7020421 (Open Web Text)

Max Activating Token Index: 821

Text #1

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.5249. Min Act: -0.1700

Data Index: 46341 (Open Web Text)

Max Activating Token Index: 111

Text #2

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.4692. Min Act: -0.1700

Data Index: 3152620 (Open Web Text)

Max Activating Token Index: 901

Text #3

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.4407. Min Act: -0.1700

Data Index: 1387421 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.4238. Min Act: -0.1700

Data Index: 6770978 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.4294. Min Act: -0.1700

Data Index: 3137885 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3804. Min Act: -0.1700

Data Index: 1875293 (Open Web Text)

Max Activating Token Index: 744

Text #7

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3571. Min Act: -0.1700

Data Index: 5120235 (Open Web Text)

Max Activating Token Index: 552

Text #8

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3245. Min Act: -0.1700

Data Index: 4149982 (Open Web Text)

Max Activating Token Index: 749

Text #9

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3310. Min Act: -0.1700

Data Index: 1595508 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3390. Min Act: -0.1700

Data Index: 808446 (Open Web Text)

Max Activating Token Index: 802

Text #11

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3544. Min Act: -0.1700

Data Index: 5441058 (Open Web Text)

Max Activating Token Index: 987

Text #12

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3178. Min Act: -0.1700

Data Index: 2232259 (Open Web Text)

Max Activating Token Index: 528

Text #13

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3530. Min Act: -0.1700

Data Index: 68926 (Open Web Text)

Max Activating Token Index: 947

Text #14

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3395. Min Act: -0.1700

Data Index: 6831101 (Open Web Text)

Max Activating Token Index: 810

Text #15

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3103. Min Act: -0.1700

Data Index: 2992008 (Open Web Text)

Max Activating Token Index: 382

Text #16

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3109. Min Act: -0.1700

Data Index: 106714 (Open Web Text)

Max Activating Token Index: 979

Text #17

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.3360. Min Act: -0.1700

Data Index: 2781887 (Open Web Text)

Max Activating Token Index: 1002

Text #18

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.2935. Min Act: -0.1700

Data Index: 1558417 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 4.5416. Min Range: -4.5416

Max Act: 4.2903. Min Act: -0.1700

Data Index: 5877397 (Open Web Text)

Max Activating Token Index: 382