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

Dataset: Open Web Text

Neuron 1650 in Layer 4

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: 3.7534. Min Range: -3.7534

Max Act: 3.7534. Min Act: -0.1700

Data Index: 2783295 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6541. Min Act: -0.1700

Data Index: 6884365 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6011. Min Act: -0.1700

Data Index: 786504 (Open Web Text)

Max Activating Token Index: 966

Text #3

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6053. Min Act: -0.1700

Data Index: 5832038 (Open Web Text)

Max Activating Token Index: 847

Text #4

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5980. Min Act: -0.1700

Data Index: 5956569 (Open Web Text)

Max Activating Token Index: 438

Text #5

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6180. Min Act: -0.1700

Data Index: 6349268 (Open Web Text)

Max Activating Token Index: 767

Text #6

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6071. Min Act: -0.1700

Data Index: 6232610 (Open Web Text)

Max Activating Token Index: 481

Text #7

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6021. Min Act: -0.1700

Data Index: 3395979 (Open Web Text)

Max Activating Token Index: 913

Text #8

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6258. Min Act: -0.1700

Data Index: 1920120 (Open Web Text)

Max Activating Token Index: 863

Text #9

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5499. Min Act: -0.1700

Data Index: 562220 (Open Web Text)

Max Activating Token Index: 875

Text #10

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5676. Min Act: -0.1700

Data Index: 2965431 (Open Web Text)

Max Activating Token Index: 891

Text #11

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5456. Min Act: -0.1700

Data Index: 3032490 (Open Web Text)

Max Activating Token Index: 958

Text #12

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5279. Min Act: -0.1700

Data Index: 2140376 (Open Web Text)

Max Activating Token Index: 849

Text #13

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5504. Min Act: -0.1700

Data Index: 7387474 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5429. Min Act: -0.1700

Data Index: 3215515 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5245. Min Act: -0.1700

Data Index: 3996161 (Open Web Text)

Max Activating Token Index: 507

Text #16

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5346. Min Act: -0.1700

Data Index: 6447505 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5343. Min Act: -0.1700

Data Index: 4085464 (Open Web Text)

Max Activating Token Index: 220

Text #18

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5298. Min Act: -0.1700

Data Index: 8105241 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5353. Min Act: -0.1700

Data Index: 4694946 (Open Web Text)

Max Activating Token Index: 590