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

Dataset: Open Web Text

Neuron 202 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: 4.8464. Min Range: -4.8464

Max Act: 4.8464. Min Act: -0.1700

Data Index: 2696457 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.7641. Min Act: -0.1700

Data Index: 4272615 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.7407. Min Act: -0.1700

Data Index: 8288320 (Open Web Text)

Max Activating Token Index: 902

Text #3

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.7477. Min Act: -0.1700

Data Index: 8709720 (Open Web Text)

Max Activating Token Index: 675

Text #4

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.7218. Min Act: -0.1700

Data Index: 4422186 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.7406. Min Act: -0.1700

Data Index: 7667428 (Open Web Text)

Max Activating Token Index: 774

Text #6

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.7148. Min Act: -0.1700

Data Index: 1855272 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6691. Min Act: -0.1700

Data Index: 8382769 (Open Web Text)

Max Activating Token Index: 119

Text #8

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6948. Min Act: -0.1700

Data Index: 5988657 (Open Web Text)

Max Activating Token Index: 824

Text #9

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6858. Min Act: -0.1700

Data Index: 5462158 (Open Web Text)

Max Activating Token Index: 136

Text #10

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6486. Min Act: -0.1700

Data Index: 1191794 (Open Web Text)

Max Activating Token Index: 628

Text #11

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6412. Min Act: -0.1700

Data Index: 3847281 (Open Web Text)

Max Activating Token Index: 233

Text #12

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6531. Min Act: -0.1700

Data Index: 182004 (Open Web Text)

Max Activating Token Index: 105

Text #13

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6226. Min Act: -0.1700

Data Index: 7270108 (Open Web Text)

Max Activating Token Index: 919

Text #14

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6184. Min Act: -0.1700

Data Index: 1554813 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.6296. Min Act: -0.1700

Data Index: 4737898 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.5955. Min Act: -0.1700

Data Index: 2143980 (Open Web Text)

Max Activating Token Index: 704

Text #17

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.5918. Min Act: -0.1700

Data Index: 8189746 (Open Web Text)

Max Activating Token Index: 142

Text #18

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.5850. Min Act: -0.1700

Data Index: 169352 (Open Web Text)

Max Activating Token Index: 128

Text #19

Max Range: 4.8464. Min Range: -4.8464

Max Act: 4.5761. Min Act: -0.1700

Data Index: 8418842 (Open Web Text)

Max Activating Token Index: 670