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

Dataset: Open Web Text

Neuron 1619 in Layer 5

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: 4.5866. Min Range: -4.5866

Max Act: 4.5866. Min Act: -0.1700

Data Index: 142387 (Open Web Text)

Max Activating Token Index: 538

Text #1

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4817. Min Act: -0.1700

Data Index: 3772572 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4911. Min Act: -0.1700

Data Index: 4619559 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4552. Min Act: -0.1700

Data Index: 8409845 (Open Web Text)

Max Activating Token Index: 326

Text #4

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4026. Min Act: -0.1700

Data Index: 5113598 (Open Web Text)

Max Activating Token Index: 234

Text #5

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4124. Min Act: -0.1700

Data Index: 1324580 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4084. Min Act: -0.1700

Data Index: 807848 (Open Web Text)

Max Activating Token Index: 637

Text #7

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3943. Min Act: -0.1700

Data Index: 271826 (Open Web Text)

Max Activating Token Index: 730

Text #8

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4127. Min Act: -0.1700

Data Index: 8505783 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.4222. Min Act: -0.1700

Data Index: 4367646 (Open Web Text)

Max Activating Token Index: 307

Text #10

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3495. Min Act: -0.1700

Data Index: 8568057 (Open Web Text)

Max Activating Token Index: 819

Text #11

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3591. Min Act: -0.1700

Data Index: 2097798 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3927. Min Act: -0.1700

Data Index: 1291131 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3996. Min Act: -0.1700

Data Index: 5043250 (Open Web Text)

Max Activating Token Index: 466

Text #14

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3126. Min Act: -0.1700

Data Index: 2394323 (Open Web Text)

Max Activating Token Index: 300

Text #15

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3307. Min Act: -0.1700

Data Index: 7698218 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3430. Min Act: -0.1700

Data Index: 4934925 (Open Web Text)

Max Activating Token Index: 368

Text #17

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.3013. Min Act: -0.1700

Data Index: 8590660 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.2522. Min Act: -0.1700

Data Index: 3017997 (Open Web Text)

Max Activating Token Index: 335

Text #19

Max Range: 4.5866. Min Range: -4.5866

Max Act: 4.2287. Min Act: -0.1700

Data Index: 6903073 (Open Web Text)

Max Activating Token Index: 357