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

Dataset: Open Web Text

Neuron 2401 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: 4.7386. Min Range: -4.7386

Max Act: 4.7386. Min Act: -0.1700

Data Index: 2674395 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.6925. Min Act: -0.1700

Data Index: 3049650 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.6152. Min Act: -0.1700

Data Index: 5135920 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.6039. Min Act: -0.1700

Data Index: 3136664 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5980. Min Act: -0.1700

Data Index: 7121747 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.6131. Min Act: -0.1700

Data Index: 4815103 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5881. Min Act: -0.1700

Data Index: 6388349 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5950. Min Act: -0.1700

Data Index: 1573082 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.6046. Min Act: -0.1700

Data Index: 5263523 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5757. Min Act: -0.1700

Data Index: 3688180 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5646. Min Act: -0.1700

Data Index: 5460024 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5573. Min Act: -0.1700

Data Index: 5308839 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5467. Min Act: -0.1700

Data Index: 1894169 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5768. Min Act: -0.1700

Data Index: 1291746 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5544. Min Act: -0.1700

Data Index: 2348670 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5777. Min Act: -0.1700

Data Index: 7893632 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5636. Min Act: -0.1700

Data Index: 3489684 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5337. Min Act: -0.1700

Data Index: 2021837 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5398. Min Act: -0.1700

Data Index: 1149456 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7386. Min Range: -4.7386

Max Act: 4.5319. Min Act: -0.1700

Data Index: 741989 (Open Web Text)

Max Activating Token Index: 4