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

Dataset: Open Web Text

Neuron 548 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: 2.8798. Min Range: -2.8798

Max Act: 2.8798. Min Act: -0.1700

Data Index: 8661394 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8603. Min Act: -0.1700

Data Index: 7762046 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8570. Min Act: -0.1700

Data Index: 5661458 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8586. Min Act: -0.1700

Data Index: 5427801 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8580. Min Act: -0.1700

Data Index: 4523683 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8412. Min Act: -0.1700

Data Index: 7436459 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8307. Min Act: -0.1700

Data Index: 5777509 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8312. Min Act: -0.1700

Data Index: 2420640 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8409. Min Act: -0.1700

Data Index: 4298918 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8226. Min Act: -0.1700

Data Index: 3185132 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8110. Min Act: -0.1700

Data Index: 4962680 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8152. Min Act: -0.1700

Data Index: 6098868 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8232. Min Act: -0.1700

Data Index: 1707348 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8154. Min Act: -0.1700

Data Index: 1480943 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8076. Min Act: -0.1700

Data Index: 311313 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8064. Min Act: -0.1700

Data Index: 4725513 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8125. Min Act: -0.1700

Data Index: 6558450 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8136. Min Act: -0.1700

Data Index: 1347786 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8136. Min Act: -0.1700

Data Index: 7158682 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8798. Min Range: -2.8798

Max Act: 2.8065. Min Act: -0.1700

Data Index: 7319140 (Open Web Text)

Max Activating Token Index: 914