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

Dataset: Open Web Text

Neuron 1740 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: 2.8342. Min Range: -2.8342

Max Act: 2.8342. Min Act: -0.1700

Data Index: 4819094 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8342. Min Act: -0.1700

Data Index: 2339505 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8342. Min Act: -0.1700

Data Index: 7343806 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8342. Min Act: -0.1700

Data Index: 6593810 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8303. Min Act: -0.1700

Data Index: 6443206 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8099. Min Act: -0.1700

Data Index: 2760659 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8179. Min Act: -0.1700

Data Index: 7476746 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8108. Min Act: -0.1700

Data Index: 4053900 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8048. Min Act: -0.1700

Data Index: 1317345 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7947. Min Act: -0.1700

Data Index: 8612150 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7966. Min Act: -0.1700

Data Index: 5544522 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.8002. Min Act: -0.1700

Data Index: 4769546 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7793. Min Act: -0.1700

Data Index: 6943867 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7798. Min Act: -0.1700

Data Index: 319758 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7874. Min Act: -0.1700

Data Index: 7057687 (Open Web Text)

Max Activating Token Index: 258

Text #15

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7911. Min Act: -0.1700

Data Index: 5297717 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7809. Min Act: -0.1700

Data Index: 5190753 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7737. Min Act: -0.1700

Data Index: 804136 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7637. Min Act: -0.1700

Data Index: 433439 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.8342. Min Range: -2.8342

Max Act: 2.7662. Min Act: -0.1700

Data Index: 5557309 (Open Web Text)

Max Activating Token Index: 6