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

Dataset: Open Web Text

Neuron 2758 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: 3.4482. Min Range: -3.4482

Max Act: 3.4482. Min Act: -0.1700

Data Index: 4761870 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.4416. Min Act: -0.1700

Data Index: 2747770 (Open Web Text)

Max Activating Token Index: 456

Text #2

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3733. Min Act: -0.1700

Data Index: 7198177 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3724. Min Act: -0.1700

Data Index: 8463365 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3486. Min Act: -0.1700

Data Index: 4713712 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3522. Min Act: -0.1700

Data Index: 1324952 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3246. Min Act: -0.1700

Data Index: 6771971 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3043. Min Act: -0.1700

Data Index: 803746 (Open Web Text)

Max Activating Token Index: 531

Text #8

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3250. Min Act: -0.1700

Data Index: 6273530 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3106. Min Act: -0.1700

Data Index: 7842911 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3051. Min Act: -0.1700

Data Index: 1643172 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2965. Min Act: -0.1700

Data Index: 7494804 (Open Web Text)

Max Activating Token Index: 178

Text #12

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2883. Min Act: -0.1700

Data Index: 8099407 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.3025. Min Act: -0.1700

Data Index: 3411616 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2894. Min Act: -0.1700

Data Index: 1567906 (Open Web Text)

Max Activating Token Index: 636

Text #15

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2704. Min Act: -0.1700

Data Index: 2675343 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2611. Min Act: -0.1700

Data Index: 4834262 (Open Web Text)

Max Activating Token Index: 501

Text #17

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2812. Min Act: -0.1700

Data Index: 7890664 (Open Web Text)

Max Activating Token Index: 892

Text #18

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2616. Min Act: -0.1700

Data Index: 142389 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 3.4482. Min Range: -3.4482

Max Act: 3.2564. Min Act: -0.1700

Data Index: 122420 (Open Web Text)

Max Activating Token Index: 514