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

Dataset: Open Web Text

Neuron 1579 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: 2.0452. Min Range: -2.0452

Max Act: 2.0452. Min Act: -0.1700

Data Index: 782743 (Open Web Text)

Max Activating Token Index: 696

Text #1

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9842. Min Act: -0.1700

Data Index: 2969166 (Open Web Text)

Max Activating Token Index: 939

Text #2

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9871. Min Act: -0.1700

Data Index: 409845 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 2.0452. Min Range: -2.0452

Max Act: 2.0038. Min Act: -0.1700

Data Index: 5159845 (Open Web Text)

Max Activating Token Index: 64

Text #4

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9751. Min Act: -0.1700

Data Index: 5091766 (Open Web Text)

Max Activating Token Index: 875

Text #5

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9766. Min Act: -0.1700

Data Index: 8731977 (Open Web Text)

Max Activating Token Index: 651

Text #6

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9645. Min Act: -0.1700

Data Index: 3575619 (Open Web Text)

Max Activating Token Index: 571

Text #7

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9584. Min Act: -0.1700

Data Index: 7327446 (Open Web Text)

Max Activating Token Index: 547

Text #8

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9596. Min Act: -0.1700

Data Index: 5608981 (Open Web Text)

Max Activating Token Index: 773

Text #9

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9449. Min Act: -0.1700

Data Index: 4845507 (Open Web Text)

Max Activating Token Index: 630

Text #10

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9388. Min Act: -0.1700

Data Index: 7834635 (Open Web Text)

Max Activating Token Index: 461

Text #11

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9786. Min Act: -0.1700

Data Index: 1144366 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9480. Min Act: -0.1700

Data Index: 5698751 (Open Web Text)

Max Activating Token Index: 778

Text #13

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9708. Min Act: -0.1700

Data Index: 3527900 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9549. Min Act: -0.1700

Data Index: 8075275 (Open Web Text)

Max Activating Token Index: 311

Text #15

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9535. Min Act: -0.1700

Data Index: 4108077 (Open Web Text)

Max Activating Token Index: 758

Text #16

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9443. Min Act: -0.1700

Data Index: 3405583 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9214. Min Act: -0.1700

Data Index: 8060448 (Open Web Text)

Max Activating Token Index: 1001

Text #18

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9297. Min Act: -0.1700

Data Index: 2085966 (Open Web Text)

Max Activating Token Index: 223

Text #19

Max Range: 2.0452. Min Range: -2.0452

Max Act: 1.9239. Min Act: -0.1700

Data Index: 5926280 (Open Web Text)

Max Activating Token Index: 700