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

Dataset: Open Web Text

Neuron 1659 in Layer 1

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: 1.6244. Min Range: -1.6244

Max Act: 1.6244. Min Act: -0.1700

Data Index: 5655642 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5586. Min Act: -0.1700

Data Index: 1640920 (Open Web Text)

Max Activating Token Index: 116

Text #2

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5480. Min Act: -0.1674

Data Index: 2236292 (Open Web Text)

Max Activating Token Index: 764

Text #3

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5457. Min Act: -0.1700

Data Index: 6363116 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5354. Min Act: -0.1695

Data Index: 5769543 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5309. Min Act: -0.1700

Data Index: 8792511 (Open Web Text)

Max Activating Token Index: 587

Text #6

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5305. Min Act: -0.1693

Data Index: 5769542 (Open Web Text)

Max Activating Token Index: 773

Text #7

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5174. Min Act: -0.1700

Data Index: 4758876 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5186. Min Act: -0.1700

Data Index: 6349886 (Open Web Text)

Max Activating Token Index: 99

Text #9

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5087. Min Act: -0.1700

Data Index: 4228954 (Open Web Text)

Max Activating Token Index: 534

Text #10

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5044. Min Act: -0.1671

Data Index: 6470319 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5126. Min Act: -0.1700

Data Index: 1744126 (Open Web Text)

Max Activating Token Index: 705

Text #12

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5012. Min Act: -0.1700

Data Index: 200395 (Open Web Text)

Max Activating Token Index: 732

Text #13

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5008. Min Act: -0.1699

Data Index: 1572561 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.4985. Min Act: -0.1696

Data Index: 7080102 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5026. Min Act: -0.1700

Data Index: 6497857 (Open Web Text)

Max Activating Token Index: 802

Text #16

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.5076. Min Act: -0.1700

Data Index: 252210 (Open Web Text)

Max Activating Token Index: 190

Text #17

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.4920. Min Act: -0.1674

Data Index: 766733 (Open Web Text)

Max Activating Token Index: 626

Text #18

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.4946. Min Act: -0.1700

Data Index: 3820429 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 1.6244. Min Range: -1.6244

Max Act: 1.4779. Min Act: -0.1698

Data Index: 540865 (Open Web Text)

Max Activating Token Index: 977