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

Dataset: Open Web Text

Neuron 259 in Layer 5

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: 4.0985. Min Range: -4.0985

Max Act: 4.0985. Min Act: -0.1700

Data Index: 3847306 (Open Web Text)

Max Activating Token Index: 599

Text #1

Max Range: 4.0985. Min Range: -4.0985

Max Act: 4.0884. Min Act: -0.1700

Data Index: 4084056 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 4.0985. Min Range: -4.0985

Max Act: 4.0421. Min Act: -0.1700

Data Index: 4858831 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 4.0985. Min Range: -4.0985

Max Act: 4.0104. Min Act: -0.1700

Data Index: 872519 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9913. Min Act: -0.1700

Data Index: 4028248 (Open Web Text)

Max Activating Token Index: 725

Text #5

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9719. Min Act: -0.1700

Data Index: 4828273 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1050679 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9867. Min Act: -0.1700

Data Index: 1629403 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9708. Min Act: -0.1700

Data Index: 7653009 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9488. Min Act: -0.1700

Data Index: 6603622 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9709. Min Act: -0.1700

Data Index: 3528538 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9968. Min Act: -0.1700

Data Index: 1221371 (Open Web Text)

Max Activating Token Index: 155

Text #12

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9058. Min Act: -0.1700

Data Index: 3731661 (Open Web Text)

Max Activating Token Index: 652

Text #13

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9036. Min Act: -0.1700

Data Index: 2649587 (Open Web Text)

Max Activating Token Index: 497

Text #14

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9308. Min Act: -0.1700

Data Index: 8163433 (Open Web Text)

Max Activating Token Index: 678

Text #15

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.8941. Min Act: -0.1700

Data Index: 6742485 (Open Web Text)

Max Activating Token Index: 916

Text #16

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9136. Min Act: -0.1700

Data Index: 8182814 (Open Web Text)

Max Activating Token Index: 952

Text #17

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9309. Min Act: -0.1700

Data Index: 7013491 (Open Web Text)

Max Activating Token Index: 50

Text #18

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.8846. Min Act: -0.1700

Data Index: 5289173 (Open Web Text)

Max Activating Token Index: 579

Text #19

Max Range: 4.0985. Min Range: -4.0985

Max Act: 3.9245. Min Act: -0.1700

Data Index: 4667703 (Open Web Text)

Max Activating Token Index: 537