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

Dataset: Open Web Text

Neuron 1972 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: 4.9602. Min Range: -4.9602

Max Act: 4.9565. Min Act: -0.1700

Data Index: 8087374 (Open Web Text)

Max Activating Token Index: 245

Text #1

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.9602. Min Act: -0.1700

Data Index: 8196078 (Open Web Text)

Max Activating Token Index: 159

Text #2

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8932. Min Act: -0.1700

Data Index: 2660770 (Open Web Text)

Max Activating Token Index: 411

Text #3

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.9094. Min Act: -0.1700

Data Index: 7590653 (Open Web Text)

Max Activating Token Index: 182

Text #4

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.9237. Min Act: -0.1700

Data Index: 7015187 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8622. Min Act: -0.1700

Data Index: 6666201 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8591. Min Act: -0.1700

Data Index: 6937445 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8509. Min Act: -0.1700

Data Index: 8498951 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7973. Min Act: -0.1700

Data Index: 6211797 (Open Web Text)

Max Activating Token Index: 179

Text #9

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8458. Min Act: -0.1700

Data Index: 4700171 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7946. Min Act: -0.1700

Data Index: 3201279 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8081. Min Act: -0.1700

Data Index: 3285617 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7910. Min Act: -0.1700

Data Index: 4157351 (Open Web Text)

Max Activating Token Index: 45

Text #13

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7985. Min Act: -0.1700

Data Index: 1658457 (Open Web Text)

Max Activating Token Index: 526

Text #14

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7840. Min Act: -0.1700

Data Index: 4491282 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7923. Min Act: -0.1700

Data Index: 6254066 (Open Web Text)

Max Activating Token Index: 528

Text #16

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7930. Min Act: -0.1700

Data Index: 2113048 (Open Web Text)

Max Activating Token Index: 101

Text #17

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8031. Min Act: -0.1700

Data Index: 6692862 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.8101. Min Act: -0.1700

Data Index: 1385090 (Open Web Text)

Max Activating Token Index: 200

Text #19

Max Range: 4.9602. Min Range: -4.9602

Max Act: 4.7939. Min Act: -0.1700

Data Index: 5698086 (Open Web Text)

Max Activating Token Index: 72