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

Dataset: Open Web Text

Neuron 877 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: 2.7966. Min Range: -2.7966

Max Act: 2.7966. Min Act: -0.1700

Data Index: 2216348 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7649. Min Act: -0.1700

Data Index: 6580905 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7623. Min Act: -0.1700

Data Index: 1338184 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7597. Min Act: -0.1700

Data Index: 4669364 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7231. Min Act: -0.1700

Data Index: 7449561 (Open Web Text)

Max Activating Token Index: 991

Text #5

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7119. Min Act: -0.1700

Data Index: 7943184 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7136. Min Act: -0.1700

Data Index: 4702602 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.7145. Min Act: -0.1700

Data Index: 2994067 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6815. Min Act: -0.1700

Data Index: 4306963 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6775. Min Act: -0.1700

Data Index: 5934006 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6826. Min Act: -0.1700

Data Index: 8166811 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6567. Min Act: -0.1700

Data Index: 3212082 (Open Web Text)

Max Activating Token Index: 886

Text #12

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1831108 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6629. Min Act: -0.1700

Data Index: 1454032 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6614. Min Act: -0.1700

Data Index: 4010262 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6631. Min Act: -0.1700

Data Index: 2445580 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6572. Min Act: -0.1700

Data Index: 2483357 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6542. Min Act: -0.1700

Data Index: 4760515 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6603. Min Act: -0.1700

Data Index: 104076 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.7966. Min Range: -2.7966

Max Act: 2.6603. Min Act: -0.1700

Data Index: 7045448 (Open Web Text)

Max Activating Token Index: 5