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

Dataset: Open Web Text

Neuron 1376 in Layer 4

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: 3.4436. Min Range: -3.4436

Max Act: 3.4436. Min Act: -0.1700

Data Index: 5802891 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.4275. Min Act: -0.1700

Data Index: 7515658 (Open Web Text)

Max Activating Token Index: 294

Text #2

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.3228. Min Act: -0.1700

Data Index: 4089642 (Open Web Text)

Max Activating Token Index: 209

Text #3

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.3299. Min Act: -0.1700

Data Index: 2893213 (Open Web Text)

Max Activating Token Index: 71

Text #4

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.3034. Min Act: -0.1700

Data Index: 1414009 (Open Web Text)

Max Activating Token Index: 110

Text #5

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2848. Min Act: -0.1700

Data Index: 1414017 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2834. Min Act: -0.1700

Data Index: 1485422 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2265. Min Act: -0.1700

Data Index: 3055176 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2270. Min Act: -0.1700

Data Index: 5434134 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2188. Min Act: -0.1700

Data Index: 7286018 (Open Web Text)

Max Activating Token Index: 936

Text #10

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.1953. Min Act: -0.1700

Data Index: 1552914 (Open Web Text)

Max Activating Token Index: 622

Text #11

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2285. Min Act: -0.1700

Data Index: 7225109 (Open Web Text)

Max Activating Token Index: 855

Text #12

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2234. Min Act: -0.1700

Data Index: 6831621 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2149. Min Act: -0.1700

Data Index: 2416264 (Open Web Text)

Max Activating Token Index: 698

Text #14

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2074. Min Act: -0.1700

Data Index: 8590059 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.1946. Min Act: -0.1700

Data Index: 8629424 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.2159. Min Act: -0.1700

Data Index: 2733938 (Open Web Text)

Max Activating Token Index: 649

Text #17

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.1839. Min Act: -0.1700

Data Index: 8287648 (Open Web Text)

Max Activating Token Index: 425

Text #18

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.1737. Min Act: -0.1700

Data Index: 3977953 (Open Web Text)

Max Activating Token Index: 372

Text #19

Max Range: 3.4436. Min Range: -3.4436

Max Act: 3.1887. Min Act: -0.1700

Data Index: 5646032 (Open Web Text)

Max Activating Token Index: 715