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

Dataset: Open Web Text

Neuron 1368 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: 5.2559. Min Range: -5.2559

Max Act: 5.2559. Min Act: -0.1700

Data Index: 5651349 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1293. Min Act: -0.1700

Data Index: 4843961 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1443. Min Act: -0.1700

Data Index: 3482448 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1063. Min Act: -0.1700

Data Index: 1219079 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0959. Min Act: -0.1700

Data Index: 4033272 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1168. Min Act: -0.1700

Data Index: 3953913 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.1168. Min Act: -0.1700

Data Index: 2066018 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0418. Min Act: -0.1700

Data Index: 4488478 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0291. Min Act: -0.1700

Data Index: 4803505 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0217. Min Act: -0.1700

Data Index: 2483208 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0372. Min Act: -0.1700

Data Index: 6315599 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0268. Min Act: -0.1700

Data Index: 2250409 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0231. Min Act: -0.1700

Data Index: 3545615 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0231. Min Act: -0.1700

Data Index: 758014 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0241. Min Act: -0.1700

Data Index: 8736261 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0483. Min Act: -0.1700

Data Index: 8534571 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0171. Min Act: -0.1700

Data Index: 7188419 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0184. Min Act: -0.1700

Data Index: 6486887 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0499. Min Act: -0.1700

Data Index: 58606 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.2559. Min Range: -5.2559

Max Act: 5.0082. Min Act: -0.1700

Data Index: 6192871 (Open Web Text)

Max Activating Token Index: 4