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

Dataset: Open Web Text

Neuron 1582 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: 1.4267. Min Range: -1.4267

Max Act: 1.4267. Min Act: -0.1425

Data Index: 8602924 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3963. Min Act: -0.1461

Data Index: 8620996 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3933. Min Act: -0.1700

Data Index: 7590176 (Open Web Text)

Max Activating Token Index: 290

Text #3

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3433. Min Act: -0.1700

Data Index: 3526949 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3547. Min Act: -0.1700

Data Index: 1102805 (Open Web Text)

Max Activating Token Index: 535

Text #5

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3278. Min Act: -0.1700

Data Index: 4719633 (Open Web Text)

Max Activating Token Index: 987

Text #6

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3210. Min Act: -0.1700

Data Index: 6598846 (Open Web Text)

Max Activating Token Index: 609

Text #7

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3103. Min Act: -0.1700

Data Index: 4262572 (Open Web Text)

Max Activating Token Index: 833

Text #8

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3064. Min Act: -0.1700

Data Index: 837573 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2927. Min Act: -0.0848

Data Index: 3724017 (Open Web Text)

Max Activating Token Index: 610

Text #10

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2963. Min Act: -0.1700

Data Index: 5692915 (Open Web Text)

Max Activating Token Index: 24

Text #11

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.3078. Min Act: -0.1700

Data Index: 1358958 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2977. Min Act: -0.1700

Data Index: 4007464 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2949. Min Act: -0.1323

Data Index: 6898624 (Open Web Text)

Max Activating Token Index: 543

Text #14

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2742. Min Act: -0.1700

Data Index: 4864990 (Open Web Text)

Max Activating Token Index: 566

Text #15

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2847. Min Act: -0.1700

Data Index: 6087767 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2800. Min Act: -0.0848

Data Index: 1233278 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2710. Min Act: -0.1700

Data Index: 7200993 (Open Web Text)

Max Activating Token Index: 171

Text #18

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2683. Min Act: -0.1700

Data Index: 2303831 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 1.4267. Min Range: -1.4267

Max Act: 1.2665. Min Act: -0.1637

Data Index: 6017835 (Open Web Text)

Max Activating Token Index: 917