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

Dataset: Open Web Text

Neuron 777 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: 3.3785. Min Range: -3.3785

Max Act: 3.3785. Min Act: -0.1700

Data Index: 6108978 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3694. Min Act: -0.1700

Data Index: 840405 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3389. Min Act: -0.1700

Data Index: 975158 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3457. Min Act: -0.1700

Data Index: 7615546 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3488. Min Act: -0.1700

Data Index: 370646 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3457. Min Act: -0.1700

Data Index: 7476525 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3593. Min Act: -0.1700

Data Index: 6112323 (Open Web Text)

Max Activating Token Index: 418

Text #7

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3335. Min Act: -0.1700

Data Index: 3360528 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3192. Min Act: -0.1700

Data Index: 6333917 (Open Web Text)

Max Activating Token Index: 457

Text #9

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3172. Min Act: -0.1700

Data Index: 6714279 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3175. Min Act: -0.1700

Data Index: 6263394 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3132. Min Act: -0.1700

Data Index: 7106122 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3368. Min Act: -0.1700

Data Index: 1531165 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3148. Min Act: -0.1700

Data Index: 5141002 (Open Web Text)

Max Activating Token Index: 724

Text #14

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3314. Min Act: -0.1700

Data Index: 2338869 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3048. Min Act: -0.1700

Data Index: 3764860 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.2985. Min Act: -0.1700

Data Index: 2095411 (Open Web Text)

Max Activating Token Index: 12

Text #17

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.2942. Min Act: -0.1700

Data Index: 7318927 (Open Web Text)

Max Activating Token Index: 516

Text #18

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3073. Min Act: -0.1700

Data Index: 684150 (Open Web Text)

Max Activating Token Index: 486

Text #19

Max Range: 3.3785. Min Range: -3.3785

Max Act: 3.3001. Min Act: -0.1700

Data Index: 1015382 (Open Web Text)

Max Activating Token Index: 486