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

Dataset: Open Web Text

Neuron 699 in Layer 1

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: 6.7212. Min Range: -6.7212

Max Act: 6.7212. Min Act: -0.1700

Data Index: 8794173 (Open Web Text)

Max Activating Token Index: 49

Text #1

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5927. Min Act: -0.1700

Data Index: 2534959 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5520. Min Act: -0.1700

Data Index: 3116169 (Open Web Text)

Max Activating Token Index: 340

Text #3

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5420. Min Act: -0.1700

Data Index: 3561407 (Open Web Text)

Max Activating Token Index: 592

Text #4

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5509. Min Act: -0.1700

Data Index: 6886055 (Open Web Text)

Max Activating Token Index: 1019

Text #5

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4945. Min Act: -0.1700

Data Index: 7234133 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4907. Min Act: -0.1700

Data Index: 569900 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4980. Min Act: -0.1700

Data Index: 3045822 (Open Web Text)

Max Activating Token Index: 534

Text #8

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5123. Min Act: -0.1700

Data Index: 4345048 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5042. Min Act: -0.1700

Data Index: 2923465 (Open Web Text)

Max Activating Token Index: 100

Text #10

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4961. Min Act: -0.1700

Data Index: 2724909 (Open Web Text)

Max Activating Token Index: 775

Text #11

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4831. Min Act: -0.1700

Data Index: 582208 (Open Web Text)

Max Activating Token Index: 312

Text #12

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.5113. Min Act: -0.1700

Data Index: 7446495 (Open Web Text)

Max Activating Token Index: 41

Text #13

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4702. Min Act: -0.1700

Data Index: 1370134 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4744. Min Act: -0.1700

Data Index: 5337329 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4666. Min Act: -0.1700

Data Index: 2567182 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4656. Min Act: -0.1700

Data Index: 585931 (Open Web Text)

Max Activating Token Index: 97

Text #17

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4588. Min Act: -0.1700

Data Index: 807030 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4870. Min Act: -0.1700

Data Index: 1741854 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 6.7212. Min Range: -6.7212

Max Act: 6.4783. Min Act: -0.1700

Data Index: 1831080 (Open Web Text)

Max Activating Token Index: 642