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

Dataset: Open Web Text

Neuron 2006 in Layer 3

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: 4.2159. Min Range: -4.2159

Max Act: 4.2159. Min Act: -0.1700

Data Index: 8792578 (Open Web Text)

Max Activating Token Index: 644

Text #1

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1729. Min Act: -0.1700

Data Index: 6392229 (Open Web Text)

Max Activating Token Index: 798

Text #2

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.1654. Min Act: -0.1700

Data Index: 6392221 (Open Web Text)

Max Activating Token Index: 269

Text #3

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0829. Min Act: -0.1700

Data Index: 456557 (Open Web Text)

Max Activating Token Index: 522

Text #4

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0533. Min Act: -0.1700

Data Index: 830317 (Open Web Text)

Max Activating Token Index: 161

Text #5

Max Range: 4.2159. Min Range: -4.2159

Max Act: 4.0121. Min Act: -0.1700

Data Index: 6232860 (Open Web Text)

Max Activating Token Index: 362

Text #6

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9657. Min Act: -0.1700

Data Index: 4843991 (Open Web Text)

Max Activating Token Index: 799

Text #7

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9836. Min Act: -0.1700

Data Index: 197530 (Open Web Text)

Max Activating Token Index: 54

Text #8

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9131. Min Act: -0.1700

Data Index: 6828320 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9760. Min Act: -0.1700

Data Index: 200793 (Open Web Text)

Max Activating Token Index: 639

Text #10

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9225. Min Act: -0.1700

Data Index: 7234134 (Open Web Text)

Max Activating Token Index: 511

Text #11

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9384. Min Act: -0.1700

Data Index: 6519762 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9089. Min Act: -0.1700

Data Index: 8286665 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.9064. Min Act: -0.1700

Data Index: 2471030 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8530. Min Act: -0.1700

Data Index: 8668890 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8917. Min Act: -0.1700

Data Index: 6156347 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8643. Min Act: -0.1700

Data Index: 7585821 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8902. Min Act: -0.1700

Data Index: 1934065 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8797. Min Act: -0.1700

Data Index: 4604210 (Open Web Text)

Max Activating Token Index: 760

Text #19

Max Range: 4.2159. Min Range: -4.2159

Max Act: 3.8621. Min Act: -0.1700

Data Index: 4022100 (Open Web Text)

Max Activating Token Index: 244