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

Dataset: Open Web Text

Neuron 638 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: 1.4923. Min Range: -1.4923

Max Act: 1.4923. Min Act: -0.1200

Data Index: 3435956 (Open Web Text)

Max Activating Token Index: 677

Text #1

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4672. Min Act: -0.1200

Data Index: 1753833 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4552. Min Act: -0.1200

Data Index: 8062431 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4584. Min Act: -0.1200

Data Index: 2138550 (Open Web Text)

Max Activating Token Index: 527

Text #4

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4497. Min Act: -0.1200

Data Index: 1753837 (Open Web Text)

Max Activating Token Index: 215

Text #5

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4384. Min Act: -0.1200

Data Index: 5692358 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4358. Min Act: -0.1200

Data Index: 2958809 (Open Web Text)

Max Activating Token Index: 450

Text #7

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4333. Min Act: -0.1481

Data Index: 4180269 (Open Web Text)

Max Activating Token Index: 788

Text #8

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4256. Min Act: -0.1200

Data Index: 3782604 (Open Web Text)

Max Activating Token Index: 693

Text #9

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4189. Min Act: -0.1200

Data Index: 5773075 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4271. Min Act: -0.1570

Data Index: 938843 (Open Web Text)

Max Activating Token Index: 307

Text #11

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4181. Min Act: -0.1200

Data Index: 5949163 (Open Web Text)

Max Activating Token Index: 420

Text #12

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4156. Min Act: -0.1200

Data Index: 5136086 (Open Web Text)

Max Activating Token Index: 423

Text #13

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4090. Min Act: -0.1200

Data Index: 861621 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4201. Min Act: -0.1506

Data Index: 2137068 (Open Web Text)

Max Activating Token Index: 353

Text #15

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4025. Min Act: -0.1200

Data Index: 2806504 (Open Web Text)

Max Activating Token Index: 508

Text #16

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4161. Min Act: -0.1200

Data Index: 7042445 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4033. Min Act: -0.1200

Data Index: 1887763 (Open Web Text)

Max Activating Token Index: 520

Text #18

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4050. Min Act: -0.1200

Data Index: 1000497 (Open Web Text)

Max Activating Token Index: 684

Text #19

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4060. Min Act: -0.1259

Data Index: 3076254 (Open Web Text)

Max Activating Token Index: 529