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

Dataset: Open Web Text

Neuron 2462 in Layer 1

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: 1.9534. Min Range: -1.9534

Max Act: 1.9534. Min Act: -0.1700

Data Index: 113054 (Open Web Text)

Max Activating Token Index: 502

Text #1

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8697. Min Act: -0.1700

Data Index: 5232812 (Open Web Text)

Max Activating Token Index: 440

Text #2

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8703. Min Act: -0.1700

Data Index: 8582593 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8692. Min Act: -0.1700

Data Index: 5819987 (Open Web Text)

Max Activating Token Index: 499

Text #4

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8703. Min Act: -0.1700

Data Index: 464835 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8703. Min Act: -0.1700

Data Index: 8038399 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8597. Min Act: -0.1700

Data Index: 3569995 (Open Web Text)

Max Activating Token Index: 495

Text #7

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8532. Min Act: -0.1700

Data Index: 4740820 (Open Web Text)

Max Activating Token Index: 723

Text #8

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8536. Min Act: -0.1700

Data Index: 1277579 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8480. Min Act: -0.1700

Data Index: 8009742 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8401. Min Act: -0.1700

Data Index: 7084649 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8481. Min Act: -0.1700

Data Index: 7315285 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8471. Min Act: -0.1700

Data Index: 2771448 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8258. Min Act: -0.1700

Data Index: 24190 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8279. Min Act: -0.1700

Data Index: 5809255 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8232. Min Act: -0.1700

Data Index: 3109591 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8428. Min Act: -0.1700

Data Index: 6001385 (Open Web Text)

Max Activating Token Index: 455

Text #17

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8273. Min Act: -0.1700

Data Index: 2750031 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8113. Min Act: -0.1700

Data Index: 2532129 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 1.9534. Min Range: -1.9534

Max Act: 1.8303. Min Act: -0.1700

Data Index: 5638548 (Open Web Text)

Max Activating Token Index: 415