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

Dataset: Open Web Text

Neuron 18 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: 3.9877. Min Range: -3.9877

Max Act: 3.9877. Min Act: -0.1700

Data Index: 6572040 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9835. Min Act: -0.1700

Data Index: 8405257 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9613. Min Act: -0.1700

Data Index: 6992363 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9399. Min Act: -0.1700

Data Index: 5794716 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9480. Min Act: -0.1700

Data Index: 7229852 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9382. Min Act: -0.1700

Data Index: 4060436 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9185. Min Act: -0.1700

Data Index: 763258 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9128. Min Act: -0.1700

Data Index: 3101373 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8990. Min Act: -0.1700

Data Index: 1504579 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8922. Min Act: -0.1700

Data Index: 4756947 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.9053. Min Act: -0.1700

Data Index: 1496108 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8719. Min Act: -0.1700

Data Index: 6102469 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8538. Min Act: -0.1700

Data Index: 5679571 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8667. Min Act: -0.1700

Data Index: 5121312 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8839. Min Act: -0.1700

Data Index: 5045371 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8575. Min Act: -0.1700

Data Index: 1339847 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8560. Min Act: -0.1700

Data Index: 4999292 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8594. Min Act: -0.1700

Data Index: 4936786 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8660. Min Act: -0.1700

Data Index: 674274 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9877. Min Range: -3.9877

Max Act: 3.8509. Min Act: -0.1700

Data Index: 4907901 (Open Web Text)

Max Activating Token Index: 6