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

Dataset: Open Web Text

Neuron 907 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: 2.1225. Min Range: -2.1225

Max Act: 2.1104. Min Act: -0.1627

Data Index: 1015321 (Open Web Text)

Max Activating Token Index: 233

Text #1

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.1225. Min Act: -0.1700

Data Index: 2258516 (Open Web Text)

Max Activating Token Index: 463

Text #2

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0972. Min Act: -0.1678

Data Index: 7831840 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1683

Data Index: 145046 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1700

Data Index: 1719092 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1663

Data Index: 61334 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1700

Data Index: 58438 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1700

Data Index: 3669472 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1700

Data Index: 1986388 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1672

Data Index: 2738823 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1697

Data Index: 2724850 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1699

Data Index: 2514994 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1673

Data Index: 3173709 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1694

Data Index: 3179277 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1686

Data Index: 334540 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1697

Data Index: 4319237 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1669

Data Index: 2481210 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1556

Data Index: 293604 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1678

Data Index: 2592923 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.1225. Min Range: -2.1225

Max Act: 2.0587. Min Act: -0.1659

Data Index: 3711040 (Open Web Text)

Max Activating Token Index: 5