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

Dataset: Open Web Text

Neuron 3000 in Layer 0

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: 3.0229. Min Range: -3.0229

Max Act: 3.0229. Min Act: -0.1700

Data Index: 7196061 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.0229. Min Range: -3.0229

Max Act: 3.0072. Min Act: -0.1700

Data Index: 954078 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9919. Min Act: -0.1700

Data Index: 546511 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9717. Min Act: -0.1700

Data Index: 3088179 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9798. Min Act: -0.1700

Data Index: 7425355 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9746. Min Act: -0.1700

Data Index: 3033992 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9673. Min Act: -0.1700

Data Index: 6017941 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9475. Min Act: -0.1700

Data Index: 4078192 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9478. Min Act: -0.1700

Data Index: 6124051 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9361. Min Act: -0.1700

Data Index: 8405950 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9168. Min Act: -0.1700

Data Index: 23768 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9029. Min Act: -0.1700

Data Index: 7250147 (Open Web Text)

Max Activating Token Index: 495

Text #12

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9010. Min Act: -0.1700

Data Index: 64045 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8965. Min Act: -0.1700

Data Index: 5135963 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.9057. Min Act: -0.1700

Data Index: 5349312 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8977. Min Act: -0.1700

Data Index: 4796000 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8990. Min Act: -0.1700

Data Index: 895770 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8863. Min Act: -0.1700

Data Index: 1443702 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8949. Min Act: -0.1700

Data Index: 3868662 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.0229. Min Range: -3.0229

Max Act: 2.8901. Min Act: -0.1700

Data Index: 7243349 (Open Web Text)

Max Activating Token Index: 5