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

Dataset: Open Web Text

Neuron 2078 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: 5.5260. Min Range: -5.5260

Max Act: 5.5260. Min Act: -0.1700

Data Index: 355664 (Open Web Text)

Max Activating Token Index: 914

Text #1

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.3977. Min Act: -0.1700

Data Index: 959555 (Open Web Text)

Max Activating Token Index: 989

Text #2

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.3786. Min Act: -0.1700

Data Index: 7246463 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.3414. Min Act: -0.1700

Data Index: 799240 (Open Web Text)

Max Activating Token Index: 847

Text #4

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.3681. Min Act: -0.1700

Data Index: 6774688 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.2505. Min Act: -0.1700

Data Index: 6377376 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.2130. Min Act: -0.1700

Data Index: 3987733 (Open Web Text)

Max Activating Token Index: 898

Text #7

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.1210. Min Act: -0.1700

Data Index: 3587250 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.1303. Min Act: -0.1700

Data Index: 681378 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.1094. Min Act: -0.1700

Data Index: 941062 (Open Web Text)

Max Activating Token Index: 61

Text #10

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.1011. Min Act: -0.1700

Data Index: 3303040 (Open Web Text)

Max Activating Token Index: 634

Text #11

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0481. Min Act: -0.1700

Data Index: 1161984 (Open Web Text)

Max Activating Token Index: 616

Text #12

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0395. Min Act: -0.1700

Data Index: 840957 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0603. Min Act: -0.1700

Data Index: 6210975 (Open Web Text)

Max Activating Token Index: 611

Text #14

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0745. Min Act: -0.1700

Data Index: 1617104 (Open Web Text)

Max Activating Token Index: 834

Text #15

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0420. Min Act: -0.1700

Data Index: 4823892 (Open Web Text)

Max Activating Token Index: 239

Text #16

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0156. Min Act: -0.1700

Data Index: 3263128 (Open Web Text)

Max Activating Token Index: 430

Text #17

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0298. Min Act: -0.1700

Data Index: 6012928 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 5.5260. Min Range: -5.5260

Max Act: 4.9991. Min Act: -0.1700

Data Index: 4100469 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 5.5260. Min Range: -5.5260

Max Act: 5.0583. Min Act: -0.1700

Data Index: 1635324 (Open Web Text)

Max Activating Token Index: 684