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

Dataset: Open Web Text

Neuron 2723 in Layer 6

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: 3.5887. Min Range: -3.5887

Max Act: 3.5887. Min Act: -0.1700

Data Index: 7146073 (Open Web Text)

Max Activating Token Index: 588

Text #1

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.5207. Min Act: -0.1700

Data Index: 570608 (Open Web Text)

Max Activating Token Index: 713

Text #2

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.3971. Min Act: -0.1700

Data Index: 8403458 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.3991. Min Act: -0.1700

Data Index: 888266 (Open Web Text)

Max Activating Token Index: 94

Text #4

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.3693. Min Act: -0.1700

Data Index: 2195723 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2935. Min Act: -0.1700

Data Index: 6401668 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.3141. Min Act: -0.1700

Data Index: 1167618 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2314. Min Act: -0.1700

Data Index: 6202591 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2400. Min Act: -0.1700

Data Index: 6529504 (Open Web Text)

Max Activating Token Index: 395

Text #9

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2338. Min Act: -0.1700

Data Index: 2949536 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2117. Min Act: -0.1700

Data Index: 5348342 (Open Web Text)

Max Activating Token Index: 531

Text #11

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2146. Min Act: -0.1700

Data Index: 3250481 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2021. Min Act: -0.1700

Data Index: 1513885 (Open Web Text)

Max Activating Token Index: 610

Text #13

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.1880. Min Act: -0.1700

Data Index: 7385012 (Open Web Text)

Max Activating Token Index: 631

Text #14

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.1904. Min Act: -0.1700

Data Index: 528578 (Open Web Text)

Max Activating Token Index: 930

Text #15

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.1935. Min Act: -0.1700

Data Index: 8789123 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.1876. Min Act: -0.1700

Data Index: 4685744 (Open Web Text)

Max Activating Token Index: 193

Text #17

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.2042. Min Act: -0.1700

Data Index: 4652379 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.1664. Min Act: -0.1700

Data Index: 7376964 (Open Web Text)

Max Activating Token Index: 572

Text #19

Max Range: 3.5887. Min Range: -3.5887

Max Act: 3.1711. Min Act: -0.1700

Data Index: 3742858 (Open Web Text)

Max Activating Token Index: 469