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

Dataset: Open Web Text

Neuron 43 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: 5.6915. Min Range: -5.6915

Max Act: 5.6915. Min Act: -0.1700

Data Index: 3649636 (Open Web Text)

Max Activating Token Index: 947

Text #1

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.6106. Min Act: -0.1700

Data Index: 4527314 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5796. Min Act: -0.1700

Data Index: 2516841 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.6010. Min Act: -0.1700

Data Index: 6050647 (Open Web Text)

Max Activating Token Index: 317

Text #4

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5233. Min Act: -0.1700

Data Index: 4972541 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5500. Min Act: -0.1700

Data Index: 6377591 (Open Web Text)

Max Activating Token Index: 744

Text #6

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5577. Min Act: -0.1700

Data Index: 5796366 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5277. Min Act: -0.1700

Data Index: 4118277 (Open Web Text)

Max Activating Token Index: 895

Text #8

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5205. Min Act: -0.1700

Data Index: 4982954 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5773. Min Act: -0.1700

Data Index: 1279751 (Open Web Text)

Max Activating Token Index: 808

Text #10

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5293. Min Act: -0.1700

Data Index: 8525575 (Open Web Text)

Max Activating Token Index: 821

Text #11

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.4825. Min Act: -0.1700

Data Index: 4665432 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5096. Min Act: -0.1700

Data Index: 4119597 (Open Web Text)

Max Activating Token Index: 870

Text #13

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5265. Min Act: -0.1700

Data Index: 5333327 (Open Web Text)

Max Activating Token Index: 626

Text #14

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.4934. Min Act: -0.1700

Data Index: 3390534 (Open Web Text)

Max Activating Token Index: 704

Text #15

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.4986. Min Act: -0.1700

Data Index: 3990414 (Open Web Text)

Max Activating Token Index: 583

Text #16

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5069. Min Act: -0.1700

Data Index: 3448498 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.4618. Min Act: -0.1700

Data Index: 4499874 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.4230. Min Act: -0.1700

Data Index: 4754602 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 5.6915. Min Range: -5.6915

Max Act: 5.5025. Min Act: -0.1700

Data Index: 4269025 (Open Web Text)

Max Activating Token Index: 1019