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

Dataset: Open Web Text

Neuron 1430 in Layer 5

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: 5.2032. Min Range: -5.2032

Max Act: 5.2018. Min Act: -0.1700

Data Index: 5748663 (Open Web Text)

Max Activating Token Index: 645

Text #1

Max Range: 5.2032. Min Range: -5.2032

Max Act: 5.2032. Min Act: -0.1700

Data Index: 8037283 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 5.2032. Min Range: -5.2032

Max Act: 5.0578. Min Act: -0.1700

Data Index: 6770743 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9989. Min Act: -0.1700

Data Index: 2161780 (Open Web Text)

Max Activating Token Index: 284

Text #4

Max Range: 5.2032. Min Range: -5.2032

Max Act: 5.0039. Min Act: -0.1700

Data Index: 3305986 (Open Web Text)

Max Activating Token Index: 767

Text #5

Max Range: 5.2032. Min Range: -5.2032

Max Act: 5.0067. Min Act: -0.1700

Data Index: 6520142 (Open Web Text)

Max Activating Token Index: 594

Text #6

Max Range: 5.2032. Min Range: -5.2032

Max Act: 5.0458. Min Act: -0.1700

Data Index: 5148156 (Open Web Text)

Max Activating Token Index: 803

Text #7

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9790. Min Act: -0.1700

Data Index: 2266552 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9797. Min Act: -0.1700

Data Index: 4458034 (Open Web Text)

Max Activating Token Index: 183

Text #9

Max Range: 5.2032. Min Range: -5.2032

Max Act: 5.0171. Min Act: -0.1700

Data Index: 1901173 (Open Web Text)

Max Activating Token Index: 458

Text #10

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9706. Min Act: -0.1700

Data Index: 5185230 (Open Web Text)

Max Activating Token Index: 441

Text #11

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9330. Min Act: -0.1700

Data Index: 8459459 (Open Web Text)

Max Activating Token Index: 554

Text #12

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9575. Min Act: -0.1700

Data Index: 4116810 (Open Web Text)

Max Activating Token Index: 68

Text #13

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9213. Min Act: -0.1700

Data Index: 1511247 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9495. Min Act: -0.1700

Data Index: 7872441 (Open Web Text)

Max Activating Token Index: 638

Text #15

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9333. Min Act: -0.1700

Data Index: 5542984 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9580. Min Act: -0.1700

Data Index: 5220481 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9707. Min Act: -0.1700

Data Index: 2746639 (Open Web Text)

Max Activating Token Index: 420

Text #18

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9466. Min Act: -0.1700

Data Index: 5107515 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 5.2032. Min Range: -5.2032

Max Act: 4.9228. Min Act: -0.1700

Data Index: 860628 (Open Web Text)

Max Activating Token Index: 218