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

Dataset: Open Web Text

Neuron 137 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: 3.3426. Min Range: -3.3426

Max Act: 3.3426. Min Act: -0.1700

Data Index: 1273754 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.2773. Min Act: -0.1700

Data Index: 4553145 (Open Web Text)

Max Activating Token Index: 167

Text #2

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1444. Min Act: -0.1700

Data Index: 5082368 (Open Web Text)

Max Activating Token Index: 245

Text #3

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1372. Min Act: -0.1700

Data Index: 8720115 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0939. Min Act: -0.1700

Data Index: 6672897 (Open Web Text)

Max Activating Token Index: 228

Text #5

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.1044. Min Act: -0.1700

Data Index: 1632566 (Open Web Text)

Max Activating Token Index: 670

Text #6

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0726. Min Act: -0.1700

Data Index: 8333737 (Open Web Text)

Max Activating Token Index: 393

Text #7

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0961. Min Act: -0.1700

Data Index: 2668549 (Open Web Text)

Max Activating Token Index: 435

Text #8

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0962. Min Act: -0.1700

Data Index: 1069353 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0358. Min Act: -0.1700

Data Index: 4612939 (Open Web Text)

Max Activating Token Index: 868

Text #10

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0436. Min Act: -0.1700

Data Index: 6806947 (Open Web Text)

Max Activating Token Index: 892

Text #11

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0525. Min Act: -0.1700

Data Index: 48411 (Open Web Text)

Max Activating Token Index: 302

Text #12

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0270. Min Act: -0.1700

Data Index: 5235018 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0003. Min Act: -0.1700

Data Index: 3674654 (Open Web Text)

Max Activating Token Index: 759

Text #14

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0246. Min Act: -0.1700

Data Index: 4911156 (Open Web Text)

Max Activating Token Index: 890

Text #15

Max Range: 3.3426. Min Range: -3.3426

Max Act: 3.0175. Min Act: -0.1700

Data Index: 6183653 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 3.3426. Min Range: -3.3426

Max Act: 2.9965. Min Act: -0.1700

Data Index: 970422 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 3.3426. Min Range: -3.3426

Max Act: 2.9963. Min Act: -0.1700

Data Index: 8440626 (Open Web Text)

Max Activating Token Index: 197

Text #18

Max Range: 3.3426. Min Range: -3.3426

Max Act: 2.9866. Min Act: -0.1700

Data Index: 6279481 (Open Web Text)

Max Activating Token Index: 188

Text #19

Max Range: 3.3426. Min Range: -3.3426

Max Act: 2.9950. Min Act: -0.1700

Data Index: 8459996 (Open Web Text)

Max Activating Token Index: 803