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

Dataset: Open Web Text

Neuron 1364 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: 3.8539. Min Range: -3.8539

Max Act: 3.8539. Min Act: -0.1700

Data Index: 8265629 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7865. Min Act: -0.1700

Data Index: 5648899 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7989. Min Act: -0.1700

Data Index: 6756311 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7730. Min Act: -0.1700

Data Index: 3816701 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7774. Min Act: -0.1700

Data Index: 2279567 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7842. Min Act: -0.1700

Data Index: 2851450 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7813. Min Act: -0.1700

Data Index: 1838814 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7641. Min Act: -0.1700

Data Index: 1047414 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7269. Min Act: -0.1700

Data Index: 8037604 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7530. Min Act: -0.1700

Data Index: 2929476 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7434. Min Act: -0.1700

Data Index: 7551773 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7310. Min Act: -0.1700

Data Index: 2459302 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7280. Min Act: -0.1700

Data Index: 6756310 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7319. Min Act: -0.1700

Data Index: 2173236 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7003. Min Act: -0.1700

Data Index: 4276536 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6929. Min Act: -0.1700

Data Index: 6826873 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6993. Min Act: -0.1700

Data Index: 986387 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6943. Min Act: -0.1700

Data Index: 2298165 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7229. Min Act: -0.1700

Data Index: 2216137 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6946. Min Act: -0.1700

Data Index: 4439346 (Open Web Text)

Max Activating Token Index: 4