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

Dataset: Open Web Text

Neuron 554 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: 2.8562. Min Range: -2.8562

Max Act: 2.8562. Min Act: -0.1700

Data Index: 6585266 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.8210. Min Act: -0.1700

Data Index: 4701470 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.8070. Min Act: -0.1700

Data Index: 1859974 (Open Web Text)

Max Activating Token Index: 316

Text #3

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7816. Min Act: -0.1700

Data Index: 4757387 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7816. Min Act: -0.1700

Data Index: 4457695 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7719. Min Act: -0.1700

Data Index: 7834036 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7816. Min Act: -0.1700

Data Index: 5201666 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7708. Min Act: -0.1700

Data Index: 4596065 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7664. Min Act: -0.1700

Data Index: 4552101 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7633. Min Act: -0.1700

Data Index: 3176199 (Open Web Text)

Max Activating Token Index: 65

Text #10

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7666. Min Act: -0.1700

Data Index: 6266957 (Open Web Text)

Max Activating Token Index: 23

Text #11

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7707. Min Act: -0.1700

Data Index: 1290389 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7737. Min Act: -0.1700

Data Index: 3973292 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7512. Min Act: -0.1700

Data Index: 2242073 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7568. Min Act: -0.1700

Data Index: 8578576 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7482. Min Act: -0.1700

Data Index: 7017224 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7377. Min Act: -0.1700

Data Index: 1792845 (Open Web Text)

Max Activating Token Index: 683

Text #17

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7599. Min Act: -0.1700

Data Index: 6073811 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7238. Min Act: -0.1700

Data Index: 1829611 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.8562. Min Range: -2.8562

Max Act: 2.7278. Min Act: -0.1700

Data Index: 5744241 (Open Web Text)

Max Activating Token Index: 626