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

Dataset: Open Web Text

Neuron 2158 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: 6.9546. Min Range: -6.9546

Max Act: 6.9078. Min Act: -0.1700

Data Index: 5305010 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.9356. Min Act: -0.1700

Data Index: 5832384 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.9168. Min Act: -0.1700

Data Index: 1326064 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.9546. Min Act: -0.1700

Data Index: 2475377 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.9287. Min Act: -0.1700

Data Index: 2234542 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8431. Min Act: -0.1700

Data Index: 5049257 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8526. Min Act: -0.1700

Data Index: 3321082 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8631. Min Act: -0.1700

Data Index: 3195783 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8663. Min Act: -0.1700

Data Index: 2751431 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8414. Min Act: -0.1700

Data Index: 8603119 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8734. Min Act: -0.1700

Data Index: 8537316 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8393. Min Act: -0.1700

Data Index: 2375623 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8775. Min Act: -0.1700

Data Index: 8500383 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8785. Min Act: -0.1700

Data Index: 2105033 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8587. Min Act: -0.1700

Data Index: 7539696 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8964. Min Act: -0.1700

Data Index: 7279973 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8416. Min Act: -0.1700

Data Index: 467162 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8533. Min Act: -0.1700

Data Index: 6237687 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8659. Min Act: -0.1700

Data Index: 4579875 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 6.9546. Min Range: -6.9546

Max Act: 6.8067. Min Act: -0.1700

Data Index: 3998748 (Open Web Text)

Max Activating Token Index: 4