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

Dataset: Open Web Text

Neuron 2723 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: 7.4299. Min Range: -7.4299

Max Act: 7.4299. Min Act: -0.1700

Data Index: 428281 (Open Web Text)

Max Activating Token Index: 607

Text #1

Max Range: 7.4299. Min Range: -7.4299

Max Act: 7.4187. Min Act: -0.1700

Data Index: 428279 (Open Web Text)

Max Activating Token Index: 826

Text #2

Max Range: 7.4299. Min Range: -7.4299

Max Act: 7.3646. Min Act: -0.1700

Data Index: 1721771 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 7.4299. Min Range: -7.4299

Max Act: 7.1225. Min Act: -0.1700

Data Index: 428278 (Open Web Text)

Max Activating Token Index: 973

Text #4

Max Range: 7.4299. Min Range: -7.4299

Max Act: 7.1040. Min Act: -0.1700

Data Index: 1721777 (Open Web Text)

Max Activating Token Index: 756

Text #5

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.8806. Min Act: -0.1700

Data Index: 1721780 (Open Web Text)

Max Activating Token Index: 931

Text #6

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.9697. Min Act: -0.1700

Data Index: 1721775 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.6933. Min Act: -0.1700

Data Index: 1721774 (Open Web Text)

Max Activating Token Index: 84

Text #8

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5766. Min Act: -0.1700

Data Index: 5732878 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.6092. Min Act: -0.1700

Data Index: 3751228 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5298. Min Act: -0.1700

Data Index: 2855958 (Open Web Text)

Max Activating Token Index: 914

Text #11

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5260. Min Act: -0.1700

Data Index: 2624792 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5618. Min Act: -0.1700

Data Index: 4859712 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5833. Min Act: -0.1700

Data Index: 2624781 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5243. Min Act: -0.1700

Data Index: 2624790 (Open Web Text)

Max Activating Token Index: 303

Text #15

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5727. Min Act: -0.1700

Data Index: 5013159 (Open Web Text)

Max Activating Token Index: 399

Text #16

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5337. Min Act: -0.1700

Data Index: 2624780 (Open Web Text)

Max Activating Token Index: 717

Text #17

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5375. Min Act: -0.1700

Data Index: 7915161 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.5065. Min Act: -0.1700

Data Index: 6397928 (Open Web Text)

Max Activating Token Index: 687

Text #19

Max Range: 7.4299. Min Range: -7.4299

Max Act: 6.4691. Min Act: -0.1699

Data Index: 428280 (Open Web Text)

Max Activating Token Index: 389