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

Dataset: Open Web Text

Neuron 1774 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: 3.6721. Min Range: -3.6721

Max Act: 3.6721. Min Act: -0.1700

Data Index: 2662980 (Open Web Text)

Max Activating Token Index: 301

Text #1

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5984. Min Act: -0.1700

Data Index: 6174496 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5798. Min Act: -0.1700

Data Index: 1275187 (Open Web Text)

Max Activating Token Index: 295

Text #3

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5424. Min Act: -0.1700

Data Index: 8526124 (Open Web Text)

Max Activating Token Index: 457

Text #4

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5799. Min Act: -0.1700

Data Index: 1769946 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5555. Min Act: -0.1700

Data Index: 946272 (Open Web Text)

Max Activating Token Index: 212

Text #6

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5459. Min Act: -0.1700

Data Index: 16341 (Open Web Text)

Max Activating Token Index: 909

Text #7

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5560. Min Act: -0.1700

Data Index: 4801056 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5333. Min Act: -0.1700

Data Index: 8269218 (Open Web Text)

Max Activating Token Index: 471

Text #9

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5180. Min Act: -0.1700

Data Index: 1773549 (Open Web Text)

Max Activating Token Index: 214

Text #10

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5059. Min Act: -0.1700

Data Index: 7010584 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5266. Min Act: -0.1700

Data Index: 177752 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5143. Min Act: -0.1700

Data Index: 3565952 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.4840. Min Act: -0.1700

Data Index: 1114755 (Open Web Text)

Max Activating Token Index: 729

Text #14

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5031. Min Act: -0.1700

Data Index: 7692894 (Open Web Text)

Max Activating Token Index: 853

Text #15

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.5023. Min Act: -0.1700

Data Index: 6805812 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.4833. Min Act: -0.1700

Data Index: 1367995 (Open Web Text)

Max Activating Token Index: 216

Text #17

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.4946. Min Act: -0.1700

Data Index: 5620885 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.4711. Min Act: -0.1700

Data Index: 3814713 (Open Web Text)

Max Activating Token Index: 359

Text #19

Max Range: 3.6721. Min Range: -3.6721

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1543367 (Open Web Text)

Max Activating Token Index: 168