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

Dataset: Open Web Text

Neuron 887 in Layer 0

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: 5.4838. Min Range: -5.4838

Max Act: 5.4838. Min Act: -0.1700

Data Index: 23408 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4743. Min Act: -0.1700

Data Index: 5214824 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4373. Min Act: -0.1700

Data Index: 5215843 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4431. Min Act: -0.1700

Data Index: 7924351 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4433. Min Act: -0.1700

Data Index: 8079354 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4239. Min Act: -0.1700

Data Index: 8316429 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4024. Min Act: -0.1700

Data Index: 5662556 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3848. Min Act: -0.1700

Data Index: 7519867 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4028. Min Act: -0.1700

Data Index: 7676498 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4246. Min Act: -0.1700

Data Index: 3461315 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.4067. Min Act: -0.1700

Data Index: 4856297 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3982. Min Act: -0.1700

Data Index: 1116343 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3931. Min Act: -0.1700

Data Index: 2471863 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3890. Min Act: -0.1700

Data Index: 4922557 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3716. Min Act: -0.1700

Data Index: 4759676 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3557. Min Act: -0.1700

Data Index: 4527718 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3775. Min Act: -0.1700

Data Index: 1842838 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3767. Min Act: -0.1700

Data Index: 418900 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3648. Min Act: -0.1700

Data Index: 4351214 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.4838. Min Range: -5.4838

Max Act: 5.3567. Min Act: -0.1700

Data Index: 1768784 (Open Web Text)

Max Activating Token Index: 3