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

Dataset: Open Web Text

Neuron 654 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: 2.0211. Min Range: -2.0211

Max Act: 2.0211. Min Act: -0.1700

Data Index: 3031610 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9810. Min Act: -0.1700

Data Index: 3797208 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9441. Min Act: -0.1700

Data Index: 7267974 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9375. Min Act: -0.1700

Data Index: 7938133 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9378. Min Act: -0.1700

Data Index: 5059062 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9125. Min Act: -0.1700

Data Index: 7629886 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9100. Min Act: -0.1700

Data Index: 3941677 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9100. Min Act: -0.1700

Data Index: 5467698 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9100. Min Act: -0.1700

Data Index: 2511436 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.9100. Min Act: -0.1700

Data Index: 5944591 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8967. Min Act: -0.1700

Data Index: 2554776 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8672. Min Act: -0.1700

Data Index: 3780892 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8709. Min Act: -0.1699

Data Index: 8532614 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8709. Min Act: -0.1700

Data Index: 6795836 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8492. Min Act: -0.1700

Data Index: 6772302 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8492. Min Act: -0.1700

Data Index: 4391175 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8298. Min Act: -0.1700

Data Index: 1672675 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8268. Min Act: -0.1700

Data Index: 7754001 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8132. Min Act: -0.1700

Data Index: 3159824 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.0211. Min Range: -2.0211

Max Act: 1.8181. Min Act: -0.1700

Data Index: 5853825 (Open Web Text)

Max Activating Token Index: 7