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

Dataset: Open Web Text

Neuron 2756 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: 3.6248. Min Range: -3.6248

Max Act: 3.6248. Min Act: -0.1700

Data Index: 7115029 (Open Web Text)

Max Activating Token Index: 751

Text #1

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.5949. Min Act: -0.1700

Data Index: 7115021 (Open Web Text)

Max Activating Token Index: 830

Text #2

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.5085. Min Act: -0.1700

Data Index: 2830660 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.5076. Min Act: -0.1700

Data Index: 1539486 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.5028. Min Act: -0.1700

Data Index: 520156 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4579. Min Act: -0.1700

Data Index: 3327602 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4460. Min Act: -0.1700

Data Index: 365729 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4564. Min Act: -0.1700

Data Index: 4066243 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4465. Min Act: -0.1700

Data Index: 4618434 (Open Web Text)

Max Activating Token Index: 687

Text #9

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4443. Min Act: -0.1700

Data Index: 2225424 (Open Web Text)

Max Activating Token Index: 405

Text #10

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4437. Min Act: -0.1700

Data Index: 272488 (Open Web Text)

Max Activating Token Index: 397

Text #11

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4427. Min Act: -0.1700

Data Index: 45788 (Open Web Text)

Max Activating Token Index: 458

Text #12

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4281. Min Act: -0.1700

Data Index: 7287212 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4184. Min Act: -0.1700

Data Index: 2592054 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4305. Min Act: -0.1700

Data Index: 670903 (Open Web Text)

Max Activating Token Index: 106

Text #15

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4104. Min Act: -0.1700

Data Index: 6375816 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4154. Min Act: -0.1700

Data Index: 6860551 (Open Web Text)

Max Activating Token Index: 356

Text #17

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4072. Min Act: -0.1700

Data Index: 6943467 (Open Web Text)

Max Activating Token Index: 686

Text #18

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.4113. Min Act: -0.1700

Data Index: 3672223 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 3.6248. Min Range: -3.6248

Max Act: 3.3998. Min Act: -0.1700

Data Index: 6911994 (Open Web Text)

Max Activating Token Index: 375