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

Dataset: Open Web Text

Neuron 2094 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: 1.0009. Min Range: -1.0009

Max Act: 0.9991. Min Act: -0.0935

Data Index: 1462216 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.0009. Min Range: -1.0009

Max Act: 1.0009. Min Act: -0.1230

Data Index: 5669039 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9922. Min Act: -0.0779

Data Index: 5787117 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9843. Min Act: -0.0950

Data Index: 6971004 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9856. Min Act: -0.0807

Data Index: 8496503 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9799. Min Act: -0.1229

Data Index: 5643650 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9812. Min Act: -0.0768

Data Index: 3694970 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9653. Min Act: -0.1150

Data Index: 5057016 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9666. Min Act: -0.1237

Data Index: 5895089 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9612. Min Act: -0.1106

Data Index: 2824761 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9631. Min Act: -0.1339

Data Index: 7945311 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9618. Min Act: -0.1081

Data Index: 3969639 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9616. Min Act: -0.0880

Data Index: 3956905 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9717. Min Act: -0.1321

Data Index: 1805655 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9606. Min Act: -0.0722

Data Index: 6389695 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9571. Min Act: -0.0995

Data Index: 2424417 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9522. Min Act: -0.1110

Data Index: 5023594 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9589. Min Act: -0.1005

Data Index: 5736038 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9564. Min Act: -0.1061

Data Index: 8408288 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9540. Min Act: -0.1135

Data Index: 5658891 (Open Web Text)

Max Activating Token Index: 1023