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

Dataset: Open Web Text

Neuron 1666 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: 4.5851. Min Range: -4.5851

Max Act: 4.5851. Min Act: -0.1683

Data Index: 4835786 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5512. Min Act: -0.1700

Data Index: 7309399 (Open Web Text)

Max Activating Token Index: 632

Text #2

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5256. Min Act: -0.1700

Data Index: 3496938 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.5066. Min Act: -0.1700

Data Index: 2731061 (Open Web Text)

Max Activating Token Index: 468

Text #4

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4681. Min Act: -0.1700

Data Index: 80497 (Open Web Text)

Max Activating Token Index: 26

Text #5

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4559. Min Act: -0.1696

Data Index: 571380 (Open Web Text)

Max Activating Token Index: 346

Text #6

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4640. Min Act: -0.1700

Data Index: 6977416 (Open Web Text)

Max Activating Token Index: 437

Text #7

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4343. Min Act: -0.1699

Data Index: 2667019 (Open Web Text)

Max Activating Token Index: 660

Text #8

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4411. Min Act: -0.1700

Data Index: 2768479 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.4119. Min Act: -0.1700

Data Index: 6824203 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3996. Min Act: -0.1699

Data Index: 6715540 (Open Web Text)

Max Activating Token Index: 386

Text #11

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3571. Min Act: -0.1700

Data Index: 7857939 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3582. Min Act: -0.1700

Data Index: 125541 (Open Web Text)

Max Activating Token Index: 747

Text #13

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3754. Min Act: -0.1700

Data Index: 5404156 (Open Web Text)

Max Activating Token Index: 477

Text #14

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3283. Min Act: -0.1700

Data Index: 333448 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3472. Min Act: -0.1697

Data Index: 3496939 (Open Web Text)

Max Activating Token Index: 53

Text #16

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3579. Min Act: -0.1700

Data Index: 6474191 (Open Web Text)

Max Activating Token Index: 370

Text #17

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.3033. Min Act: -0.1700

Data Index: 3343629 (Open Web Text)

Max Activating Token Index: 180

Text #18

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.2984. Min Act: -0.1696

Data Index: 6694806 (Open Web Text)

Max Activating Token Index: 752

Text #19

Max Range: 4.5851. Min Range: -4.5851

Max Act: 4.2888. Min Act: -0.1700

Data Index: 5216261 (Open Web Text)

Max Activating Token Index: 120