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

Dataset: Open Web Text

Neuron 2926 in Layer 1

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: 5.2061. Min Range: -5.2061

Max Act: 5.2061. Min Act: -0.1700

Data Index: 1341984 (Open Web Text)

Max Activating Token Index: 271

Text #1

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.1744. Min Act: -0.1700

Data Index: 4499825 (Open Web Text)

Max Activating Token Index: 180

Text #2

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.1613. Min Act: -0.1700

Data Index: 5915010 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.1085. Min Act: -0.1700

Data Index: 3684825 (Open Web Text)

Max Activating Token Index: 342

Text #4

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0816. Min Act: -0.1700

Data Index: 440347 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0839. Min Act: -0.1700

Data Index: 6710292 (Open Web Text)

Max Activating Token Index: 782

Text #6

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0758. Min Act: -0.1700

Data Index: 1330635 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0700. Min Act: -0.1700

Data Index: 8139218 (Open Web Text)

Max Activating Token Index: 169

Text #8

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0755. Min Act: -0.1700

Data Index: 7776254 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0300. Min Act: -0.1700

Data Index: 1011305 (Open Web Text)

Max Activating Token Index: 699

Text #10

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0596. Min Act: -0.1700

Data Index: 2395363 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0511. Min Act: -0.1700

Data Index: 3830920 (Open Web Text)

Max Activating Token Index: 635

Text #12

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0571. Min Act: -0.1700

Data Index: 5770434 (Open Web Text)

Max Activating Token Index: 844

Text #13

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0579. Min Act: -0.1700

Data Index: 5427263 (Open Web Text)

Max Activating Token Index: 727

Text #14

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0476. Min Act: -0.1700

Data Index: 3256377 (Open Web Text)

Max Activating Token Index: 571

Text #15

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0547. Min Act: -0.1700

Data Index: 7435495 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0498. Min Act: -0.1700

Data Index: 7144643 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0435. Min Act: -0.1700

Data Index: 6823605 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0429. Min Act: -0.1700

Data Index: 6447677 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 5.2061. Min Range: -5.2061

Max Act: 5.0061. Min Act: -0.1700

Data Index: 5989668 (Open Web Text)

Max Activating Token Index: 692