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

Dataset: Open Web Text

Neuron 75 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: 2.1715. Min Range: -2.1715

Max Act: 2.1715. Min Act: -0.1700

Data Index: 4186789 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.1598. Min Act: -0.1700

Data Index: 2885790 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.1400. Min Act: -0.1700

Data Index: 3555295 (Open Web Text)

Max Activating Token Index: 167

Text #3

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.1170. Min Act: -0.1700

Data Index: 8510531 (Open Web Text)

Max Activating Token Index: 325

Text #4

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0933. Min Act: -0.1700

Data Index: 148483 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0913. Min Act: -0.1700

Data Index: 3741175 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0926. Min Act: -0.1700

Data Index: 3684499 (Open Web Text)

Max Activating Token Index: 277

Text #7

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0720. Min Act: -0.1700

Data Index: 1074699 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0998. Min Act: -0.1700

Data Index: 6500616 (Open Web Text)

Max Activating Token Index: 409

Text #9

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0775. Min Act: -0.1700

Data Index: 1864274 (Open Web Text)

Max Activating Token Index: 280

Text #10

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0832. Min Act: -0.1700

Data Index: 8693791 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0737. Min Act: -0.1700

Data Index: 457969 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.1001. Min Act: -0.1700

Data Index: 7598045 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0592. Min Act: -0.1700

Data Index: 1078689 (Open Web Text)

Max Activating Token Index: 282

Text #14

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0648. Min Act: -0.1700

Data Index: 6270144 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0668. Min Act: -0.1700

Data Index: 953406 (Open Web Text)

Max Activating Token Index: 56

Text #16

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0577. Min Act: -0.1700

Data Index: 286357 (Open Web Text)

Max Activating Token Index: 549

Text #17

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0489. Min Act: -0.1700

Data Index: 7541096 (Open Web Text)

Max Activating Token Index: 877

Text #18

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0411. Min Act: -0.1700

Data Index: 6268579 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.1715. Min Range: -2.1715

Max Act: 2.0477. Min Act: -0.1700

Data Index: 3741179 (Open Web Text)

Max Activating Token Index: 5