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

Dataset: Open Web Text

Neuron 578 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: 5.4036. Min Range: -5.4036

Max Act: 5.4036. Min Act: -0.1700

Data Index: 4196028 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.3703. Min Act: -0.1700

Data Index: 8120442 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.3280. Min Act: -0.1700

Data Index: 1673661 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.3194. Min Act: -0.1700

Data Index: 2298520 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.3305. Min Act: -0.1700

Data Index: 4668415 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2827. Min Act: -0.1700

Data Index: 3339742 (Open Web Text)

Max Activating Token Index: 379

Text #6

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2451. Min Act: -0.1700

Data Index: 2434047 (Open Web Text)

Max Activating Token Index: 63

Text #7

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2714. Min Act: -0.1700

Data Index: 313618 (Open Web Text)

Max Activating Token Index: 368

Text #8

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2644. Min Act: -0.1700

Data Index: 990301 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2601. Min Act: -0.1700

Data Index: 5600960 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2872. Min Act: -0.1700

Data Index: 5489645 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2421. Min Act: -0.1700

Data Index: 1479785 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2481. Min Act: -0.1700

Data Index: 1041923 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2259. Min Act: -0.1700

Data Index: 4888167 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2455. Min Act: -0.1700

Data Index: 19451 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2539. Min Act: -0.1700

Data Index: 5990702 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2481. Min Act: -0.1700

Data Index: 4159086 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2211. Min Act: -0.1700

Data Index: 7332573 (Open Web Text)

Max Activating Token Index: 306

Text #18

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2379. Min Act: -0.1700

Data Index: 7363418 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 5.4036. Min Range: -5.4036

Max Act: 5.2249. Min Act: -0.1700

Data Index: 394280 (Open Web Text)

Max Activating Token Index: 10