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

Dataset: Open Web Text

Neuron 803 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: 2.8693. Min Range: -2.8693

Max Act: 2.8693. Min Act: -0.1700

Data Index: 5130353 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.8136. Min Act: -0.1700

Data Index: 1186321 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7967. Min Act: -0.1700

Data Index: 5415720 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7969. Min Act: -0.1700

Data Index: 8608928 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7962. Min Act: -0.1700

Data Index: 8356939 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7827. Min Act: -0.1700

Data Index: 7214174 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7922. Min Act: -0.1700

Data Index: 3894280 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7689. Min Act: -0.1700

Data Index: 7343773 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7789. Min Act: -0.1700

Data Index: 5367657 (Open Web Text)

Max Activating Token Index: 19

Text #9

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7537. Min Act: -0.1700

Data Index: 4443531 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7550. Min Act: -0.1700

Data Index: 4216557 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7456. Min Act: -0.1700

Data Index: 6653994 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7473. Min Act: -0.1700

Data Index: 3897347 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7455. Min Act: -0.1700

Data Index: 4831221 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7536. Min Act: -0.1700

Data Index: 6307131 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7396. Min Act: -0.1700

Data Index: 7236447 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7561. Min Act: -0.1700

Data Index: 6147460 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7510. Min Act: -0.1700

Data Index: 5476741 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7337. Min Act: -0.1700

Data Index: 4836103 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 2.8693. Min Range: -2.8693

Max Act: 2.7345. Min Act: -0.1700

Data Index: 4320899 (Open Web Text)

Max Activating Token Index: 6