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

Dataset: Open Web Text

Neuron 595 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: 3.6732. Min Range: -3.6732

Max Act: 3.6732. Min Act: -0.1700

Data Index: 2159994 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.6366. Min Act: -0.1700

Data Index: 4864080 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.6164. Min Act: -0.1700

Data Index: 958874 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5983. Min Act: -0.1700

Data Index: 447583 (Open Web Text)

Max Activating Token Index: 895

Text #4

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5755. Min Act: -0.1700

Data Index: 4650161 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5562. Min Act: -0.1700

Data Index: 702822 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5682. Min Act: -0.1700

Data Index: 1559671 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5625. Min Act: -0.1700

Data Index: 1967008 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5625. Min Act: -0.1700

Data Index: 5954150 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5650. Min Act: -0.1700

Data Index: 3431662 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5672. Min Act: -0.1700

Data Index: 4303383 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5675. Min Act: -0.1700

Data Index: 3023508 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5467. Min Act: -0.1700

Data Index: 6395277 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5525. Min Act: -0.1700

Data Index: 1510378 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5540. Min Act: -0.1700

Data Index: 3684834 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5590. Min Act: -0.1700

Data Index: 1062136 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5488. Min Act: -0.1700

Data Index: 6893412 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5373. Min Act: -0.1700

Data Index: 2919522 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5413. Min Act: -0.1700

Data Index: 6304368 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.6732. Min Range: -3.6732

Max Act: 3.5340. Min Act: -0.1700

Data Index: 2799770 (Open Web Text)

Max Activating Token Index: 4