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

Dataset: Open Web Text

Neuron 1168 in Layer 6

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: 3.1254. Min Range: -3.1254

Max Act: 3.1254. Min Act: -0.1700

Data Index: 4160013 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9767. Min Act: -0.1700

Data Index: 1511647 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9798. Min Act: -0.1700

Data Index: 4532726 (Open Web Text)

Max Activating Token Index: 565

Text #3

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9818. Min Act: -0.1700

Data Index: 5689520 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9584. Min Act: -0.1700

Data Index: 2661374 (Open Web Text)

Max Activating Token Index: 868

Text #5

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9639. Min Act: -0.1700

Data Index: 3690017 (Open Web Text)

Max Activating Token Index: 318

Text #6

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9544. Min Act: -0.1700

Data Index: 8120024 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9178. Min Act: -0.1700

Data Index: 1621200 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9335. Min Act: -0.1700

Data Index: 4649106 (Open Web Text)

Max Activating Token Index: 327

Text #9

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9500. Min Act: -0.1700

Data Index: 283785 (Open Web Text)

Max Activating Token Index: 139

Text #10

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9488. Min Act: -0.1700

Data Index: 2384331 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9254. Min Act: -0.1700

Data Index: 7016493 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9541. Min Act: -0.1700

Data Index: 7473747 (Open Web Text)

Max Activating Token Index: 719

Text #13

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9263. Min Act: -0.1700

Data Index: 6778238 (Open Web Text)

Max Activating Token Index: 372

Text #14

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9179. Min Act: -0.1700

Data Index: 7638555 (Open Web Text)

Max Activating Token Index: 821

Text #15

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9201. Min Act: -0.1700

Data Index: 7726469 (Open Web Text)

Max Activating Token Index: 137

Text #16

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9000. Min Act: -0.1700

Data Index: 3893478 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9363. Min Act: -0.1700

Data Index: 8771138 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.9259. Min Act: -0.1700

Data Index: 7406893 (Open Web Text)

Max Activating Token Index: 848

Text #19

Max Range: 3.1254. Min Range: -3.1254

Max Act: 2.8999. Min Act: -0.1700

Data Index: 4597119 (Open Web Text)

Max Activating Token Index: 966