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

Dataset: Open Web Text

Neuron 1367 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: 3.8782. Min Range: -3.8782

Max Act: 3.8782. Min Act: -0.1700

Data Index: 3700261 (Open Web Text)

Max Activating Token Index: 492

Text #1

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.6461. Min Act: -0.1700

Data Index: 4195958 (Open Web Text)

Max Activating Token Index: 415

Text #2

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.5546. Min Act: -0.1700

Data Index: 8407305 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.5381. Min Act: -0.1700

Data Index: 3181417 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.5346. Min Act: -0.1700

Data Index: 657978 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.5177. Min Act: -0.1700

Data Index: 5286132 (Open Web Text)

Max Activating Token Index: 482

Text #6

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4761. Min Act: -0.1700

Data Index: 7897167 (Open Web Text)

Max Activating Token Index: 869

Text #7

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4784. Min Act: -0.1700

Data Index: 8407312 (Open Web Text)

Max Activating Token Index: 831

Text #8

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3519. Min Act: -0.1700

Data Index: 5664417 (Open Web Text)

Max Activating Token Index: 931

Text #9

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4176. Min Act: -0.1700

Data Index: 2504166 (Open Web Text)

Max Activating Token Index: 122

Text #10

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4084. Min Act: -0.1700

Data Index: 632226 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4137. Min Act: -0.1700

Data Index: 749546 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.4135. Min Act: -0.1700

Data Index: 3910222 (Open Web Text)

Max Activating Token Index: 893

Text #13

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3960. Min Act: -0.1700

Data Index: 4144979 (Open Web Text)

Max Activating Token Index: 973

Text #14

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3790. Min Act: -0.1700

Data Index: 1583225 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3196. Min Act: -0.1700

Data Index: 2043886 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3371. Min Act: -0.1700

Data Index: 4342540 (Open Web Text)

Max Activating Token Index: 975

Text #17

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3221. Min Act: -0.1700

Data Index: 4619149 (Open Web Text)

Max Activating Token Index: 435

Text #18

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3501. Min Act: -0.1700

Data Index: 1967331 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 3.8782. Min Range: -3.8782

Max Act: 3.3465. Min Act: -0.1700

Data Index: 636463 (Open Web Text)

Max Activating Token Index: 671