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

Dataset: Open Web Text

Neuron 416 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: 1.0866. Min Range: -1.0866

Max Act: 1.0866. Min Act: -0.1700

Data Index: 5528142 (Open Web Text)

Max Activating Token Index: 47

Text #1

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0767. Min Act: -0.1700

Data Index: 3567356 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0681. Min Act: -0.1700

Data Index: 6618116 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0637. Min Act: -0.1700

Data Index: 7900434 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0594. Min Act: -0.1700

Data Index: 2106238 (Open Web Text)

Max Activating Token Index: 38

Text #5

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0435. Min Act: -0.1700

Data Index: 8775316 (Open Web Text)

Max Activating Token Index: 40

Text #6

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0376. Min Act: -0.1700

Data Index: 6169304 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0344. Min Act: -0.1700

Data Index: 4457708 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0293. Min Act: -0.1700

Data Index: 7400323 (Open Web Text)

Max Activating Token Index: 39

Text #9

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0243. Min Act: -0.1700

Data Index: 7143375 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0371. Min Act: -0.1700

Data Index: 1271672 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0278. Min Act: -0.1700

Data Index: 1187864 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0363. Min Act: -0.1700

Data Index: 2238088 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0270. Min Act: -0.1700

Data Index: 3604783 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0228. Min Act: -0.1700

Data Index: 6202554 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0120. Min Act: -0.1700

Data Index: 4402317 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0201. Min Act: -0.1700

Data Index: 436791 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0271. Min Act: -0.1700

Data Index: 4556982 (Open Web Text)

Max Activating Token Index: 37

Text #18

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0129. Min Act: -0.1700

Data Index: 8610390 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0051. Min Act: -0.1700

Data Index: 910297 (Open Web Text)

Max Activating Token Index: 44