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

Dataset: Open Web Text

Neuron 2336 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: 5.0763. Min Range: -5.0763

Max Act: 5.0763. Min Act: -0.1700

Data Index: 6712162 (Open Web Text)

Max Activating Token Index: 227

Text #1

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.7599. Min Act: -0.1700

Data Index: 7521941 (Open Web Text)

Max Activating Token Index: 699

Text #2

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.7051. Min Act: -0.1700

Data Index: 7521942 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.6848. Min Act: -0.1700

Data Index: 5746295 (Open Web Text)

Max Activating Token Index: 738

Text #4

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.6505. Min Act: -0.1700

Data Index: 6712164 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.6849. Min Act: -0.1700

Data Index: 5910289 (Open Web Text)

Max Activating Token Index: 170

Text #6

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.6065. Min Act: -0.1700

Data Index: 8133631 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.5886. Min Act: -0.1700

Data Index: 2422103 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.5741. Min Act: -0.1700

Data Index: 6712153 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.4896. Min Act: -0.1700

Data Index: 5165347 (Open Web Text)

Max Activating Token Index: 519

Text #10

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.5195. Min Act: -0.1700

Data Index: 186452 (Open Web Text)

Max Activating Token Index: 955

Text #11

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.5655. Min Act: -0.1700

Data Index: 7587492 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.5095. Min Act: -0.1700

Data Index: 4467778 (Open Web Text)

Max Activating Token Index: 503

Text #13

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.5130. Min Act: -0.1700

Data Index: 6103235 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.4561. Min Act: -0.1700

Data Index: 6712161 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.4860. Min Act: -0.1700

Data Index: 2780334 (Open Web Text)

Max Activating Token Index: 89

Text #16

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.4054. Min Act: -0.1700

Data Index: 8134992 (Open Web Text)

Max Activating Token Index: 324

Text #17

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.4441. Min Act: -0.1700

Data Index: 719953 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.3907. Min Act: -0.1700

Data Index: 7658760 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 5.0763. Min Range: -5.0763

Max Act: 4.3890. Min Act: -0.1700

Data Index: 6772831 (Open Web Text)

Max Activating Token Index: 236