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

Dataset: Open Web Text

Neuron 1636 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: 3.0899. Min Range: -3.0899

Max Act: 3.0899. Min Act: -0.1700

Data Index: 4346738 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.9432. Min Act: -0.1700

Data Index: 862207 (Open Web Text)

Max Activating Token Index: 38

Text #2

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.9167. Min Act: -0.1700

Data Index: 1195321 (Open Web Text)

Max Activating Token Index: 63

Text #3

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.8988. Min Act: -0.1700

Data Index: 2336144 (Open Web Text)

Max Activating Token Index: 809

Text #4

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.8458. Min Act: -0.1700

Data Index: 4031673 (Open Web Text)

Max Activating Token Index: 881

Text #5

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.8439. Min Act: -0.1700

Data Index: 8722305 (Open Web Text)

Max Activating Token Index: 446

Text #6

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.8288. Min Act: -0.1700

Data Index: 1498152 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7860. Min Act: -0.1700

Data Index: 8117990 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7832. Min Act: -0.1700

Data Index: 1160262 (Open Web Text)

Max Activating Token Index: 928

Text #9

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7868. Min Act: -0.1700

Data Index: 2451440 (Open Web Text)

Max Activating Token Index: 1003

Text #10

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7677. Min Act: -0.1700

Data Index: 7939583 (Open Web Text)

Max Activating Token Index: 581

Text #11

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7802. Min Act: -0.1700

Data Index: 5134664 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7425. Min Act: -0.1700

Data Index: 1868383 (Open Web Text)

Max Activating Token Index: 306

Text #13

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7975. Min Act: -0.1700

Data Index: 1013278 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7509. Min Act: -0.1700

Data Index: 5889811 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7410. Min Act: -0.1700

Data Index: 7404358 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7452. Min Act: -0.1700

Data Index: 3260871 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7666. Min Act: -0.1700

Data Index: 5260025 (Open Web Text)

Max Activating Token Index: 804

Text #18

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7065. Min Act: -0.1700

Data Index: 3251236 (Open Web Text)

Max Activating Token Index: 749

Text #19

Max Range: 3.0899. Min Range: -3.0899

Max Act: 2.7287. Min Act: -0.1700

Data Index: 7170487 (Open Web Text)

Max Activating Token Index: 174