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

Dataset: Open Web Text

Neuron 2720 in Layer 2

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: 5.9143. Min Range: -5.9143

Max Act: 5.9143. Min Act: -0.1700

Data Index: 8319733 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.8762. Min Act: -0.1700

Data Index: 3179430 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7641. Min Act: -0.1700

Data Index: 5305070 (Open Web Text)

Max Activating Token Index: 182

Text #3

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7642. Min Act: -0.1628

Data Index: 6131945 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6692. Min Act: -0.1695

Data Index: 47515 (Open Web Text)

Max Activating Token Index: 854

Text #5

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6748. Min Act: -0.1694

Data Index: 4081059 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7492. Min Act: -0.1700

Data Index: 2832137 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7054. Min Act: -0.1700

Data Index: 4175202 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7271. Min Act: -0.1700

Data Index: 5421992 (Open Web Text)

Max Activating Token Index: 570

Text #9

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7377. Min Act: -0.1700

Data Index: 5512207 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7236. Min Act: -0.1695

Data Index: 1083590 (Open Web Text)

Max Activating Token Index: 780

Text #11

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7471. Min Act: -0.1699

Data Index: 392274 (Open Web Text)

Max Activating Token Index: 548

Text #12

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6849. Min Act: -0.1699

Data Index: 8558930 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.7185. Min Act: -0.1700

Data Index: 7497633 (Open Web Text)

Max Activating Token Index: 232

Text #14

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6321. Min Act: -0.1700

Data Index: 2442106 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6342. Min Act: -0.1700

Data Index: 2180778 (Open Web Text)

Max Activating Token Index: 831

Text #16

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6089. Min Act: -0.1699

Data Index: 6303148 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.6475. Min Act: -0.1699

Data Index: 2767475 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.5988. Min Act: -0.1699

Data Index: 5358649 (Open Web Text)

Max Activating Token Index: 260

Text #19

Max Range: 5.9143. Min Range: -5.9143

Max Act: 5.5693. Min Act: -0.1700

Data Index: 1281367 (Open Web Text)

Max Activating Token Index: 400