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

Dataset: Open Web Text

Neuron 1668 in Layer 2

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: 3.4681. Min Range: -3.4681

Max Act: 3.4681. Min Act: -0.1700

Data Index: 4893743 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4362. Min Act: -0.1700

Data Index: 3046102 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4549. Min Act: -0.1700

Data Index: 5661903 (Open Web Text)

Max Activating Token Index: 206

Text #3

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4388. Min Act: -0.1700

Data Index: 1892845 (Open Web Text)

Max Activating Token Index: 41

Text #4

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4507. Min Act: -0.1700

Data Index: 3710902 (Open Web Text)

Max Activating Token Index: 260

Text #5

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4355. Min Act: -0.1700

Data Index: 5808145 (Open Web Text)

Max Activating Token Index: 852

Text #6

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4218. Min Act: -0.1700

Data Index: 2346797 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4364. Min Act: -0.1700

Data Index: 6176946 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4198. Min Act: -0.1700

Data Index: 8516713 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4251. Min Act: -0.1700

Data Index: 4866439 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4147. Min Act: -0.1700

Data Index: 8659728 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.4181. Min Act: -0.1700

Data Index: 8557851 (Open Web Text)

Max Activating Token Index: 234

Text #12

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3734. Min Act: -0.1700

Data Index: 2910298 (Open Web Text)

Max Activating Token Index: 363

Text #13

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3803. Min Act: -0.1700

Data Index: 6014622 (Open Web Text)

Max Activating Token Index: 72

Text #14

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3878. Min Act: -0.1700

Data Index: 7053533 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3667. Min Act: -0.1700

Data Index: 6874702 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3448. Min Act: -0.1700

Data Index: 6375615 (Open Web Text)

Max Activating Token Index: 895

Text #17

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3458. Min Act: -0.1700

Data Index: 6155098 (Open Web Text)

Max Activating Token Index: 774

Text #18

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3345. Min Act: -0.1700

Data Index: 3764224 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 3.4681. Min Range: -3.4681

Max Act: 3.3511. Min Act: -0.1700

Data Index: 2719200 (Open Web Text)

Max Activating Token Index: 806