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

Dataset: Open Web Text

Neuron 1585 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: 4.1595. Min Range: -4.1595

Max Act: 4.1595. Min Act: -0.1700

Data Index: 1506263 (Open Web Text)

Max Activating Token Index: 656

Text #1

Max Range: 4.1595. Min Range: -4.1595

Max Act: 4.0096. Min Act: -0.1700

Data Index: 2058898 (Open Web Text)

Max Activating Token Index: 732

Text #2

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.9977. Min Act: -0.1700

Data Index: 8431664 (Open Web Text)

Max Activating Token Index: 229

Text #3

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.9646. Min Act: -0.1700

Data Index: 5221550 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.9302. Min Act: -0.1700

Data Index: 795783 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.9159. Min Act: -0.1700

Data Index: 2983654 (Open Web Text)

Max Activating Token Index: 45

Text #6

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.9084. Min Act: -0.1700

Data Index: 490149 (Open Web Text)

Max Activating Token Index: 982

Text #7

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8907. Min Act: -0.1700

Data Index: 6733568 (Open Web Text)

Max Activating Token Index: 177

Text #8

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8970. Min Act: -0.1700

Data Index: 4160521 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8568. Min Act: -0.1700

Data Index: 3189997 (Open Web Text)

Max Activating Token Index: 922

Text #10

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8688. Min Act: -0.1700

Data Index: 1401711 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8573. Min Act: -0.1700

Data Index: 4866497 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8685. Min Act: -0.1700

Data Index: 3830260 (Open Web Text)

Max Activating Token Index: 338

Text #13

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8503. Min Act: -0.1700

Data Index: 2624268 (Open Web Text)

Max Activating Token Index: 302

Text #14

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8718. Min Act: -0.1700

Data Index: 8157587 (Open Web Text)

Max Activating Token Index: 131

Text #15

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8524. Min Act: -0.1700

Data Index: 8588913 (Open Web Text)

Max Activating Token Index: 548

Text #16

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8620. Min Act: -0.1700

Data Index: 2979540 (Open Web Text)

Max Activating Token Index: 971

Text #17

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.8110. Min Act: -0.1700

Data Index: 8247686 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1243671 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 4.1595. Min Range: -4.1595

Max Act: 3.7765. Min Act: -0.1700

Data Index: 5199960 (Open Web Text)

Max Activating Token Index: 646