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

Dataset: Open Web Text

Neuron 186 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: 2.0035. Min Range: -2.0035

Max Act: 2.0035. Min Act: -0.1700

Data Index: 1509429 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9789. Min Act: -0.1700

Data Index: 1033491 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9503. Min Act: -0.1700

Data Index: 7870582 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9210. Min Act: -0.1700

Data Index: 1491690 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9239. Min Act: -0.1700

Data Index: 6972317 (Open Web Text)

Max Activating Token Index: 337

Text #5

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9169. Min Act: -0.1700

Data Index: 1615321 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9224. Min Act: -0.1700

Data Index: 1318484 (Open Web Text)

Max Activating Token Index: 297

Text #7

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8869. Min Act: -0.1700

Data Index: 8705704 (Open Web Text)

Max Activating Token Index: 328

Text #8

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8963. Min Act: -0.1700

Data Index: 7012885 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9108. Min Act: -0.1700

Data Index: 7584884 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.9004. Min Act: -0.1700

Data Index: 7103779 (Open Web Text)

Max Activating Token Index: 112

Text #11

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8781. Min Act: -0.1700

Data Index: 4058090 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8752. Min Act: -0.1700

Data Index: 8201446 (Open Web Text)

Max Activating Token Index: 602

Text #13

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8828. Min Act: -0.1700

Data Index: 4058089 (Open Web Text)

Max Activating Token Index: 366

Text #14

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8554. Min Act: -0.1700

Data Index: 3278066 (Open Web Text)

Max Activating Token Index: 151

Text #15

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8612. Min Act: -0.1700

Data Index: 1908738 (Open Web Text)

Max Activating Token Index: 391

Text #16

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8617. Min Act: -0.1700

Data Index: 3278062 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8681. Min Act: -0.1700

Data Index: 2405077 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8816. Min Act: -0.1700

Data Index: 4687981 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 2.0035. Min Range: -2.0035

Max Act: 1.8820. Min Act: -0.1700

Data Index: 1982634 (Open Web Text)

Max Activating Token Index: 989