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

Dataset: Open Web Text

Neuron 2292 in Layer 5

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: 5.6313. Min Range: -5.6313

Max Act: 5.5833. Min Act: -0.1700

Data Index: 2514611 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.6313. Min Act: -0.1700

Data Index: 521413 (Open Web Text)

Max Activating Token Index: 411

Text #2

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.6178. Min Act: -0.1700

Data Index: 586139 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.5250. Min Act: -0.1700

Data Index: 4675210 (Open Web Text)

Max Activating Token Index: 900

Text #4

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.5063. Min Act: -0.1700

Data Index: 1267339 (Open Web Text)

Max Activating Token Index: 407

Text #5

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4538. Min Act: -0.1700

Data Index: 772426 (Open Web Text)

Max Activating Token Index: 407

Text #6

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4815. Min Act: -0.1700

Data Index: 1238758 (Open Web Text)

Max Activating Token Index: 486

Text #7

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4771. Min Act: -0.1700

Data Index: 4822225 (Open Web Text)

Max Activating Token Index: 187

Text #8

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4690. Min Act: -0.1700

Data Index: 4167600 (Open Web Text)

Max Activating Token Index: 203

Text #9

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4761. Min Act: -0.1700

Data Index: 7574833 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4343. Min Act: -0.1700

Data Index: 4927821 (Open Web Text)

Max Activating Token Index: 316

Text #11

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4248. Min Act: -0.1700

Data Index: 5213836 (Open Web Text)

Max Activating Token Index: 457

Text #12

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4346. Min Act: -0.1700

Data Index: 3673035 (Open Web Text)

Max Activating Token Index: 924

Text #13

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4211. Min Act: -0.1700

Data Index: 7119997 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4056. Min Act: -0.1700

Data Index: 7664607 (Open Web Text)

Max Activating Token Index: 42

Text #15

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.3686. Min Act: -0.1700

Data Index: 2128298 (Open Web Text)

Max Activating Token Index: 270

Text #16

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4104. Min Act: -0.1700

Data Index: 3373042 (Open Web Text)

Max Activating Token Index: 953

Text #17

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4147. Min Act: -0.1700

Data Index: 200250 (Open Web Text)

Max Activating Token Index: 359

Text #18

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.3264. Min Act: -0.1700

Data Index: 2995405 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 5.6313. Min Range: -5.6313

Max Act: 5.4000. Min Act: -0.1700

Data Index: 1820812 (Open Web Text)

Max Activating Token Index: 952