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

Dataset: Open Web Text

Neuron 2721 in Layer 4

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: 4.0123. Min Range: -4.0123

Max Act: 4.0123. Min Act: -0.1700

Data Index: 3158151 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.9859. Min Act: -0.1700

Data Index: 7028047 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.9961. Min Act: -0.1700

Data Index: 5063175 (Open Web Text)

Max Activating Token Index: 650

Text #3

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.9208. Min Act: -0.1700

Data Index: 2658094 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.9153. Min Act: -0.1700

Data Index: 6039206 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8756. Min Act: -0.1700

Data Index: 2828298 (Open Web Text)

Max Activating Token Index: 381

Text #6

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8518. Min Act: -0.1700

Data Index: 3888397 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8517. Min Act: -0.1700

Data Index: 5902863 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8533. Min Act: -0.1700

Data Index: 1487503 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8390. Min Act: -0.1700

Data Index: 7564923 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8197. Min Act: -0.1700

Data Index: 6350406 (Open Web Text)

Max Activating Token Index: 669

Text #11

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8207. Min Act: -0.1700

Data Index: 2346998 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8389. Min Act: -0.1700

Data Index: 2946225 (Open Web Text)

Max Activating Token Index: 936

Text #13

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7642. Min Act: -0.1700

Data Index: 4613111 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7850. Min Act: -0.1700

Data Index: 2425480 (Open Web Text)

Max Activating Token Index: 887

Text #15

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7768. Min Act: -0.1700

Data Index: 463276 (Open Web Text)

Max Activating Token Index: 872

Text #16

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.8208. Min Act: -0.1700

Data Index: 5099644 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7677. Min Act: -0.1700

Data Index: 8393465 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7904. Min Act: -0.1700

Data Index: 8601204 (Open Web Text)

Max Activating Token Index: 803

Text #19

Max Range: 4.0123. Min Range: -4.0123

Max Act: 3.7882. Min Act: -0.1700

Data Index: 7837002 (Open Web Text)

Max Activating Token Index: 345