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

Dataset: Open Web Text

Neuron 3003 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: 5.2238. Min Range: -5.2238

Max Act: 5.2238. Min Act: -0.1700

Data Index: 2025737 (Open Web Text)

Max Activating Token Index: 283

Text #1

Max Range: 5.2238. Min Range: -5.2238

Max Act: 5.1135. Min Act: -0.1700

Data Index: 2363262 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 5.2238. Min Range: -5.2238

Max Act: 5.0751. Min Act: -0.1700

Data Index: 6049519 (Open Web Text)

Max Activating Token Index: 714

Text #3

Max Range: 5.2238. Min Range: -5.2238

Max Act: 5.0264. Min Act: -0.1700

Data Index: 1324871 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 5.2238. Min Range: -5.2238

Max Act: 5.0721. Min Act: -0.1700

Data Index: 3569953 (Open Web Text)

Max Activating Token Index: 697

Text #5

Max Range: 5.2238. Min Range: -5.2238

Max Act: 5.0064. Min Act: -0.1700

Data Index: 568898 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 5.2238. Min Range: -5.2238

Max Act: 5.0683. Min Act: -0.1700

Data Index: 8449526 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9440. Min Act: -0.1700

Data Index: 4754785 (Open Web Text)

Max Activating Token Index: 456

Text #8

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9294. Min Act: -0.1700

Data Index: 2294201 (Open Web Text)

Max Activating Token Index: 649

Text #9

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9290. Min Act: -0.1700

Data Index: 2720797 (Open Web Text)

Max Activating Token Index: 617

Text #10

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9725. Min Act: -0.1700

Data Index: 8068863 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9776. Min Act: -0.1700

Data Index: 3668247 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9568. Min Act: -0.1700

Data Index: 2088186 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9831. Min Act: -0.1700

Data Index: 1327 (Open Web Text)

Max Activating Token Index: 391

Text #14

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9222. Min Act: -0.1700

Data Index: 1832343 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9342. Min Act: -0.1700

Data Index: 2654334 (Open Web Text)

Max Activating Token Index: 217

Text #16

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9516. Min Act: -0.1700

Data Index: 6444784 (Open Web Text)

Max Activating Token Index: 236

Text #17

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9048. Min Act: -0.1700

Data Index: 5288958 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.9106. Min Act: -0.1700

Data Index: 1951935 (Open Web Text)

Max Activating Token Index: 455

Text #19

Max Range: 5.2238. Min Range: -5.2238

Max Act: 4.8885. Min Act: -0.1700

Data Index: 4461504 (Open Web Text)

Max Activating Token Index: 797