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

Dataset: Open Web Text

Neuron 1528 in Layer 6

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: 3.0534. Min Range: -3.0534

Max Act: 3.0534. Min Act: -0.1700

Data Index: 8206003 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 3.0534. Min Range: -3.0534

Max Act: 3.0235. Min Act: -0.1700

Data Index: 2078288 (Open Web Text)

Max Activating Token Index: 975

Text #2

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9930. Min Act: -0.1700

Data Index: 3217821 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9822. Min Act: -0.1700

Data Index: 397700 (Open Web Text)

Max Activating Token Index: 686

Text #4

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9942. Min Act: -0.1700

Data Index: 6074431 (Open Web Text)

Max Activating Token Index: 334

Text #5

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9602. Min Act: -0.1700

Data Index: 7866577 (Open Web Text)

Max Activating Token Index: 994

Text #6

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9888. Min Act: -0.1700

Data Index: 4301381 (Open Web Text)

Max Activating Token Index: 904

Text #7

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9658. Min Act: -0.1700

Data Index: 5845385 (Open Web Text)

Max Activating Token Index: 778

Text #8

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9728. Min Act: -0.1700

Data Index: 406142 (Open Web Text)

Max Activating Token Index: 194

Text #9

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9512. Min Act: -0.1700

Data Index: 2961681 (Open Web Text)

Max Activating Token Index: 314

Text #10

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9438. Min Act: -0.1700

Data Index: 5314160 (Open Web Text)

Max Activating Token Index: 574

Text #11

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9298. Min Act: -0.1700

Data Index: 2902823 (Open Web Text)

Max Activating Token Index: 825

Text #12

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9325. Min Act: -0.1700

Data Index: 5066975 (Open Web Text)

Max Activating Token Index: 404

Text #13

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9163. Min Act: -0.1700

Data Index: 1821385 (Open Web Text)

Max Activating Token Index: 704

Text #14

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9463. Min Act: -0.1700

Data Index: 3835280 (Open Web Text)

Max Activating Token Index: 964

Text #15

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9126. Min Act: -0.1700

Data Index: 5431313 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9333. Min Act: -0.1700

Data Index: 4983707 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9201. Min Act: -0.1700

Data Index: 8463626 (Open Web Text)

Max Activating Token Index: 886

Text #18

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.9195. Min Act: -0.1700

Data Index: 6135711 (Open Web Text)

Max Activating Token Index: 720

Text #19

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.8922. Min Act: -0.1700

Data Index: 4544686 (Open Web Text)

Max Activating Token Index: 1004