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

Dataset: Open Web Text

Neuron 341 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: 2.9730. Min Range: -2.9730

Max Act: 2.9730. Min Act: -0.1700

Data Index: 4569238 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.9352. Min Act: -0.1700

Data Index: 1984410 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.9325. Min Act: -0.1700

Data Index: 1208320 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.9078. Min Act: -0.1700

Data Index: 8088463 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.9100. Min Act: -0.1700

Data Index: 5559415 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8935. Min Act: -0.1700

Data Index: 7890151 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8947. Min Act: -0.1700

Data Index: 2156952 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8925. Min Act: -0.1700

Data Index: 5088129 (Open Web Text)

Max Activating Token Index: 55

Text #8

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8859. Min Act: -0.1700

Data Index: 7152350 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8952. Min Act: -0.1700

Data Index: 7068137 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8816. Min Act: -0.1700

Data Index: 587223 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8748. Min Act: -0.1700

Data Index: 3295026 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8842. Min Act: -0.1700

Data Index: 5033801 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8732. Min Act: -0.1700

Data Index: 6026442 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8759. Min Act: -0.1700

Data Index: 2909764 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8688. Min Act: -0.1700

Data Index: 6260712 (Open Web Text)

Max Activating Token Index: 931

Text #16

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8600. Min Act: -0.1700

Data Index: 1033580 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8504. Min Act: -0.1700

Data Index: 1777390 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8475. Min Act: -0.1700

Data Index: 4803384 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.9730. Min Range: -2.9730

Max Act: 2.8516. Min Act: -0.1700

Data Index: 2839464 (Open Web Text)

Max Activating Token Index: 604