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

Dataset: Open Web Text

Neuron 48 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: 4.1834. Min Range: -4.1834

Max Act: 4.1834. Min Act: -0.1700

Data Index: 8441977 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.1564. Min Act: -0.1700

Data Index: 6702511 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.1220. Min Act: -0.1700

Data Index: 1025593 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.1402. Min Act: -0.1700

Data Index: 625885 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0934. Min Act: -0.1700

Data Index: 2334406 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.1000. Min Act: -0.1700

Data Index: 3445043 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.1075. Min Act: -0.1700

Data Index: 6547811 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 7691201 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 2398318 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 4862657 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0546. Min Act: -0.1700

Data Index: 651707 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 2766737 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 3874688 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 1966288 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0659. Min Act: -0.1700

Data Index: 7449694 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 4707666 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0702. Min Act: -0.1700

Data Index: 478234 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0818. Min Act: -0.1700

Data Index: 1349274 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0544. Min Act: -0.1700

Data Index: 235761 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.1834. Min Range: -4.1834

Max Act: 4.0626. Min Act: -0.1700

Data Index: 8102426 (Open Web Text)

Max Activating Token Index: 9