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

Dataset: Open Web Text

Neuron 470 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: 3.8756. Min Range: -3.8756

Max Act: 3.8706. Min Act: -0.1700

Data Index: 291 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8675. Min Act: -0.1700

Data Index: 3814871 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8756. Min Act: -0.1700

Data Index: 7415366 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8740. Min Act: -0.1700

Data Index: 2475468 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8538. Min Act: -0.1700

Data Index: 877401 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8675. Min Act: -0.1700

Data Index: 3066193 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8208. Min Act: -0.1700

Data Index: 7506906 (Open Web Text)

Max Activating Token Index: 913

Text #7

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7912. Min Act: -0.1700

Data Index: 4125923 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8091. Min Act: -0.1700

Data Index: 420917 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.8168. Min Act: -0.1700

Data Index: 5423248 (Open Web Text)

Max Activating Token Index: 1003

Text #10

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7564. Min Act: -0.1700

Data Index: 3358420 (Open Web Text)

Max Activating Token Index: 958

Text #11

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7674. Min Act: -0.1700

Data Index: 1830498 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7482. Min Act: -0.1700

Data Index: 8760450 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7671. Min Act: -0.1700

Data Index: 8168600 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7728. Min Act: -0.1700

Data Index: 5430477 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7639. Min Act: -0.1700

Data Index: 965230 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7652. Min Act: -0.1700

Data Index: 8080809 (Open Web Text)

Max Activating Token Index: 106

Text #17

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7554. Min Act: -0.1700

Data Index: 7578697 (Open Web Text)

Max Activating Token Index: 645

Text #18

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7689. Min Act: -0.1700

Data Index: 4861049 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 3.8756. Min Range: -3.8756

Max Act: 3.7504. Min Act: -0.1700

Data Index: 1841025 (Open Web Text)

Max Activating Token Index: 689