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

Dataset: Open Web Text

Neuron 2708 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: 3.4568. Min Range: -3.4568

Max Act: 3.4568. Min Act: -0.1700

Data Index: 2260881 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.4563. Min Act: -0.1700

Data Index: 8667497 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3941. Min Act: -0.1700

Data Index: 5252982 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.4243. Min Act: -0.1700

Data Index: 4716262 (Open Web Text)

Max Activating Token Index: 36

Text #4

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.4193. Min Act: -0.1700

Data Index: 3974678 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3984. Min Act: -0.1700

Data Index: 3788989 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3782. Min Act: -0.1700

Data Index: 7754734 (Open Web Text)

Max Activating Token Index: 24

Text #7

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3752. Min Act: -0.1700

Data Index: 7659343 (Open Web Text)

Max Activating Token Index: 29

Text #8

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3892. Min Act: -0.1700

Data Index: 1479945 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3803. Min Act: -0.1700

Data Index: 6626551 (Open Web Text)

Max Activating Token Index: 1022

Text #10

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3866. Min Act: -0.1700

Data Index: 4309759 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3585. Min Act: -0.1700

Data Index: 6256602 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3786. Min Act: -0.1700

Data Index: 3105244 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3345. Min Act: -0.1700

Data Index: 1672817 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3485. Min Act: -0.1700

Data Index: 900553 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3521. Min Act: -0.1700

Data Index: 4157798 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3419. Min Act: -0.1700

Data Index: 4588382 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3479. Min Act: -0.1700

Data Index: 2559641 (Open Web Text)

Max Activating Token Index: 64

Text #18

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3569. Min Act: -0.1700

Data Index: 4845290 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.4568. Min Range: -3.4568

Max Act: 3.3786. Min Act: -0.1700

Data Index: 4996293 (Open Web Text)

Max Activating Token Index: 500