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

Dataset: Open Web Text

Neuron 2926 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: 5.0551. Min Range: -5.0551

Max Act: 5.0094. Min Act: -0.1700

Data Index: 4737752 (Open Web Text)

Max Activating Token Index: 754

Text #1

Max Range: 5.0551. Min Range: -5.0551

Max Act: 5.0551. Min Act: -0.1700

Data Index: 1567778 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9537. Min Act: -0.1700

Data Index: 8136395 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9817. Min Act: -0.1700

Data Index: 5753199 (Open Web Text)

Max Activating Token Index: 166

Text #4

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9724. Min Act: -0.1700

Data Index: 983838 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9464. Min Act: -0.1700

Data Index: 661223 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9159. Min Act: -0.1700

Data Index: 5803894 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9283. Min Act: -0.1700

Data Index: 7767198 (Open Web Text)

Max Activating Token Index: 420

Text #8

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.8832. Min Act: -0.1700

Data Index: 6787358 (Open Web Text)

Max Activating Token Index: 741

Text #9

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9161. Min Act: -0.1700

Data Index: 6272833 (Open Web Text)

Max Activating Token Index: 203

Text #10

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9372. Min Act: -0.1700

Data Index: 5753198 (Open Web Text)

Max Activating Token Index: 1019

Text #11

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9102. Min Act: -0.1700

Data Index: 5492858 (Open Web Text)

Max Activating Token Index: 170

Text #12

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9129. Min Act: -0.1700

Data Index: 5087224 (Open Web Text)

Max Activating Token Index: 134

Text #13

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9524. Min Act: -0.1700

Data Index: 7788466 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.8317. Min Act: -0.1700

Data Index: 3105448 (Open Web Text)

Max Activating Token Index: 874

Text #15

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9101. Min Act: -0.1700

Data Index: 581844 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.8625. Min Act: -0.1700

Data Index: 2179832 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.9063. Min Act: -0.1700

Data Index: 7380909 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.8767. Min Act: -0.1700

Data Index: 3692696 (Open Web Text)

Max Activating Token Index: 153

Text #19

Max Range: 5.0551. Min Range: -5.0551

Max Act: 4.8423. Min Act: -0.1700

Data Index: 7024858 (Open Web Text)

Max Activating Token Index: 872