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

Dataset: Open Web Text

Neuron 96 in Layer 0

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: 1.0414. Min Range: -1.0414

Max Act: 1.0386. Min Act: -0.1700

Data Index: 5578239 (Open Web Text)

Max Activating Token Index: 339

Text #1

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0414. Min Act: -0.1700

Data Index: 3393657 (Open Web Text)

Max Activating Token Index: 299

Text #2

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0091. Min Act: -0.1700

Data Index: 5578237 (Open Web Text)

Max Activating Token Index: 915

Text #3

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0180. Min Act: -0.1694

Data Index: 1045595 (Open Web Text)

Max Activating Token Index: 335

Text #4

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0042. Min Act: -0.1700

Data Index: 5809218 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9998. Min Act: -0.1700

Data Index: 1874348 (Open Web Text)

Max Activating Token Index: 320

Text #6

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0013. Min Act: -0.1699

Data Index: 4174933 (Open Web Text)

Max Activating Token Index: 325

Text #7

Max Range: 1.0414. Min Range: -1.0414

Max Act: 1.0020. Min Act: -0.1700

Data Index: 3761085 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9840. Min Act: -0.1700

Data Index: 618233 (Open Web Text)

Max Activating Token Index: 340

Text #9

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9861. Min Act: -0.1699

Data Index: 7361801 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9720. Min Act: -0.1700

Data Index: 2862517 (Open Web Text)

Max Activating Token Index: 342

Text #11

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9718. Min Act: -0.1700

Data Index: 8445668 (Open Web Text)

Max Activating Token Index: 325

Text #12

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9619. Min Act: -0.1700

Data Index: 2752035 (Open Web Text)

Max Activating Token Index: 349

Text #13

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9613. Min Act: -0.1700

Data Index: 1485005 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9552. Min Act: -0.1700

Data Index: 6462248 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9560. Min Act: -0.1700

Data Index: 2790327 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9666. Min Act: -0.1700

Data Index: 6766447 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9579. Min Act: -0.1700

Data Index: 3452057 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9683. Min Act: -0.1699

Data Index: 2010072 (Open Web Text)

Max Activating Token Index: 338

Text #19

Max Range: 1.0414. Min Range: -1.0414

Max Act: 0.9573. Min Act: -0.1700

Data Index: 2116897 (Open Web Text)

Max Activating Token Index: 361