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

Dataset: Open Web Text

Neuron 1178 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: 2.0356. Min Range: -2.0356

Max Act: 2.0356. Min Act: -0.1700

Data Index: 3078145 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.9919. Min Act: -0.1700

Data Index: 6874391 (Open Web Text)

Max Activating Token Index: 199

Text #2

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.9279. Min Act: -0.1700

Data Index: 1949544 (Open Web Text)

Max Activating Token Index: 267

Text #3

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.9403. Min Act: -0.1700

Data Index: 4079848 (Open Web Text)

Max Activating Token Index: 531

Text #4

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.9054. Min Act: -0.1700

Data Index: 7822123 (Open Web Text)

Max Activating Token Index: 557

Text #5

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.9187. Min Act: -0.1700

Data Index: 5480395 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8953. Min Act: -0.1700

Data Index: 4931099 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8939. Min Act: -0.1700

Data Index: 119739 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8910. Min Act: -0.1700

Data Index: 4199755 (Open Web Text)

Max Activating Token Index: 542

Text #9

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8718. Min Act: -0.1700

Data Index: 4389396 (Open Web Text)

Max Activating Token Index: 891

Text #10

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8766. Min Act: -0.1700

Data Index: 5359860 (Open Web Text)

Max Activating Token Index: 876

Text #11

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8986. Min Act: -0.1700

Data Index: 8495309 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8661. Min Act: -0.1700

Data Index: 8695818 (Open Web Text)

Max Activating Token Index: 759

Text #13

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8720. Min Act: -0.1700

Data Index: 441026 (Open Web Text)

Max Activating Token Index: 463

Text #14

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8531. Min Act: -0.1700

Data Index: 7020193 (Open Web Text)

Max Activating Token Index: 345

Text #15

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8593. Min Act: -0.1700

Data Index: 6314392 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8421. Min Act: -0.1700

Data Index: 6584776 (Open Web Text)

Max Activating Token Index: 626

Text #17

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8509. Min Act: -0.1700

Data Index: 852456 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8290. Min Act: -0.1700

Data Index: 1266313 (Open Web Text)

Max Activating Token Index: 723

Text #19

Max Range: 2.0356. Min Range: -2.0356

Max Act: 1.8471. Min Act: -0.1700

Data Index: 720325 (Open Web Text)

Max Activating Token Index: 494