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

Dataset: Open Web Text

Neuron 2323 in Layer 4

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: 3.4851. Min Range: -3.4851

Max Act: 3.4851. Min Act: -0.1700

Data Index: 2849779 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.4266. Min Act: -0.1700

Data Index: 6242252 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.4261. Min Act: -0.1700

Data Index: 362052 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3911. Min Act: -0.1700

Data Index: 2659700 (Open Web Text)

Max Activating Token Index: 843

Text #4

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3975. Min Act: -0.1700

Data Index: 1949755 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3963. Min Act: -0.1700

Data Index: 595602 (Open Web Text)

Max Activating Token Index: 573

Text #6

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3969. Min Act: -0.1700

Data Index: 1596857 (Open Web Text)

Max Activating Token Index: 806

Text #7

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.4001. Min Act: -0.1700

Data Index: 6245351 (Open Web Text)

Max Activating Token Index: 537

Text #8

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3852. Min Act: -0.1700

Data Index: 880460 (Open Web Text)

Max Activating Token Index: 973

Text #9

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3782. Min Act: -0.1700

Data Index: 8212118 (Open Web Text)

Max Activating Token Index: 705

Text #10

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3928. Min Act: -0.1700

Data Index: 7368564 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3786. Min Act: -0.1700

Data Index: 1148922 (Open Web Text)

Max Activating Token Index: 342

Text #12

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3665. Min Act: -0.1700

Data Index: 7244530 (Open Web Text)

Max Activating Token Index: 882

Text #13

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3848. Min Act: -0.1700

Data Index: 7618263 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3579. Min Act: -0.1700

Data Index: 4916359 (Open Web Text)

Max Activating Token Index: 51

Text #15

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3586. Min Act: -0.1700

Data Index: 6514200 (Open Web Text)

Max Activating Token Index: 1017

Text #16

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3528. Min Act: -0.1700

Data Index: 5902860 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3629. Min Act: -0.1700

Data Index: 4952290 (Open Web Text)

Max Activating Token Index: 527

Text #18

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3613. Min Act: -0.1700

Data Index: 6478552 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 3.4851. Min Range: -3.4851

Max Act: 3.3407. Min Act: -0.1700

Data Index: 3247810 (Open Web Text)

Max Activating Token Index: 63