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

Dataset: Open Web Text

Neuron 1362 in Layer 0

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: 4.8900. Min Range: -4.8900

Max Act: 4.8900. Min Act: -0.1700

Data Index: 2299830 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.7835. Min Act: -0.1700

Data Index: 526020 (Open Web Text)

Max Activating Token Index: 557

Text #2

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6895. Min Act: -0.1700

Data Index: 7938387 (Open Web Text)

Max Activating Token Index: 256

Text #3

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.7059. Min Act: -0.1700

Data Index: 2362606 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.7067. Min Act: -0.1700

Data Index: 8256138 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.7118. Min Act: -0.1700

Data Index: 3174389 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6807. Min Act: -0.1700

Data Index: 8321786 (Open Web Text)

Max Activating Token Index: 828

Text #7

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6629. Min Act: -0.1700

Data Index: 4289050 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6695. Min Act: -0.1700

Data Index: 3618238 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6721. Min Act: -0.1700

Data Index: 3212003 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6763. Min Act: -0.1700

Data Index: 214066 (Open Web Text)

Max Activating Token Index: 39

Text #11

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6811. Min Act: -0.1700

Data Index: 8763400 (Open Web Text)

Max Activating Token Index: 211

Text #12

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6753. Min Act: -0.1700

Data Index: 6839362 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6609. Min Act: -0.1700

Data Index: 43950 (Open Web Text)

Max Activating Token Index: 269

Text #14

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6697. Min Act: -0.1700

Data Index: 5952960 (Open Web Text)

Max Activating Token Index: 500

Text #15

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6593. Min Act: -0.1700

Data Index: 7883474 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6350. Min Act: -0.1700

Data Index: 7030954 (Open Web Text)

Max Activating Token Index: 695

Text #17

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6318. Min Act: -0.1700

Data Index: 2072091 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6319. Min Act: -0.1700

Data Index: 7094182 (Open Web Text)

Max Activating Token Index: 215

Text #19

Max Range: 4.8900. Min Range: -4.8900

Max Act: 4.6227. Min Act: -0.1700

Data Index: 7739594 (Open Web Text)

Max Activating Token Index: 40