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

Dataset: Open Web Text

Neuron 2963 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: 4.8535. Min Range: -4.8535

Max Act: 4.8535. Min Act: -0.1700

Data Index: 4505940 (Open Web Text)

Max Activating Token Index: 54

Text #1

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.7921. Min Act: -0.1700

Data Index: 7458906 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.7122. Min Act: -0.1697

Data Index: 5807602 (Open Web Text)

Max Activating Token Index: 772

Text #3

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.7136. Min Act: -0.1700

Data Index: 478638 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6813. Min Act: -0.1700

Data Index: 7804843 (Open Web Text)

Max Activating Token Index: 202

Text #5

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6124. Min Act: -0.1699

Data Index: 1850740 (Open Web Text)

Max Activating Token Index: 97

Text #6

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6016. Min Act: -0.1700

Data Index: 5676704 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6155. Min Act: -0.1700

Data Index: 5610060 (Open Web Text)

Max Activating Token Index: 227

Text #8

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6053. Min Act: -0.1699

Data Index: 114980 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6405. Min Act: -0.1700

Data Index: 3002950 (Open Web Text)

Max Activating Token Index: 508

Text #10

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.6231. Min Act: -0.1697

Data Index: 849731 (Open Web Text)

Max Activating Token Index: 245

Text #11

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5887. Min Act: -0.1700

Data Index: 4869290 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5599. Min Act: -0.1700

Data Index: 1700425 (Open Web Text)

Max Activating Token Index: 436

Text #13

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5364. Min Act: -0.1700

Data Index: 3217161 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5015. Min Act: -0.1700

Data Index: 5834629 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5331. Min Act: -0.1700

Data Index: 6085864 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5146. Min Act: -0.1700

Data Index: 5590312 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5090. Min Act: -0.1700

Data Index: 2369359 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5074. Min Act: -0.1700

Data Index: 7662392 (Open Web Text)

Max Activating Token Index: 294

Text #19

Max Range: 4.8535. Min Range: -4.8535

Max Act: 4.5115. Min Act: -0.1700

Data Index: 4187831 (Open Web Text)

Max Activating Token Index: 58