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

Dataset: Open Web Text

Neuron 1366 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: 3.6275. Min Range: -3.6275

Max Act: 3.6222. Min Act: -0.1700

Data Index: 7231359 (Open Web Text)

Max Activating Token Index: 166

Text #1

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.6275. Min Act: -0.1700

Data Index: 909579 (Open Web Text)

Max Activating Token Index: 154

Text #2

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5754. Min Act: -0.1700

Data Index: 621525 (Open Web Text)

Max Activating Token Index: 749

Text #3

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5682. Min Act: -0.1700

Data Index: 6342896 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5558. Min Act: -0.1700

Data Index: 2427186 (Open Web Text)

Max Activating Token Index: 256

Text #5

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4696. Min Act: -0.1700

Data Index: 2013911 (Open Web Text)

Max Activating Token Index: 612

Text #6

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5036. Min Act: -0.1700

Data Index: 8827812 (Open Web Text)

Max Activating Token Index: 932

Text #7

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5066. Min Act: -0.1700

Data Index: 532026 (Open Web Text)

Max Activating Token Index: 450

Text #8

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4782. Min Act: -0.1700

Data Index: 4785509 (Open Web Text)

Max Activating Token Index: 171

Text #9

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5016. Min Act: -0.1700

Data Index: 8564786 (Open Web Text)

Max Activating Token Index: 783

Text #10

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4438. Min Act: -0.1700

Data Index: 4157327 (Open Web Text)

Max Activating Token Index: 760

Text #11

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4827. Min Act: -0.1700

Data Index: 6987856 (Open Web Text)

Max Activating Token Index: 829

Text #12

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.5200. Min Act: -0.1700

Data Index: 3617565 (Open Web Text)

Max Activating Token Index: 881

Text #13

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4313. Min Act: -0.1700

Data Index: 4996560 (Open Web Text)

Max Activating Token Index: 285

Text #14

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4171. Min Act: -0.1700

Data Index: 1046067 (Open Web Text)

Max Activating Token Index: 153

Text #15

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4464. Min Act: -0.1700

Data Index: 8383380 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4533. Min Act: -0.1700

Data Index: 5512184 (Open Web Text)

Max Activating Token Index: 412

Text #17

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4579. Min Act: -0.1700

Data Index: 2784104 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.4210. Min Act: -0.1700

Data Index: 225901 (Open Web Text)

Max Activating Token Index: 805

Text #19

Max Range: 3.6275. Min Range: -3.6275

Max Act: 3.3973. Min Act: -0.1700

Data Index: 4638027 (Open Web Text)

Max Activating Token Index: 432