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

Dataset: Open Web Text

Neuron 1429 in Layer 2

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: 3.0783. Min Range: -3.0783

Max Act: 3.0783. Min Act: -0.1700

Data Index: 6942778 (Open Web Text)

Max Activating Token Index: 73

Text #1

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.8486. Min Act: -0.1700

Data Index: 5993201 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.8094. Min Act: -0.1700

Data Index: 3144336 (Open Web Text)

Max Activating Token Index: 350

Text #3

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.8049. Min Act: -0.1700

Data Index: 5419962 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7990. Min Act: -0.1700

Data Index: 2805821 (Open Web Text)

Max Activating Token Index: 652

Text #5

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7548. Min Act: -0.1700

Data Index: 1436665 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7741. Min Act: -0.1700

Data Index: 124012 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7649. Min Act: -0.1700

Data Index: 3936616 (Open Web Text)

Max Activating Token Index: 538

Text #8

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7659. Min Act: -0.1700

Data Index: 192345 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7459. Min Act: -0.1700

Data Index: 656883 (Open Web Text)

Max Activating Token Index: 449

Text #10

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7677. Min Act: -0.1700

Data Index: 7753017 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7545. Min Act: -0.1700

Data Index: 1436669 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7401. Min Act: -0.1700

Data Index: 2789842 (Open Web Text)

Max Activating Token Index: 310

Text #13

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7382. Min Act: -0.1700

Data Index: 3204486 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7485. Min Act: -0.1700

Data Index: 595289 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7295. Min Act: -0.1700

Data Index: 3098219 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7306. Min Act: -0.1700

Data Index: 1436671 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7430. Min Act: -0.1700

Data Index: 5971984 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7193. Min Act: -0.1700

Data Index: 1436670 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 3.0783. Min Range: -3.0783

Max Act: 2.7194. Min Act: -0.1700

Data Index: 3413501 (Open Web Text)

Max Activating Token Index: 79