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

Dataset: Open Web Text

Neuron 2367 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: 0.8685. Min Range: -0.8685

Max Act: 0.8685. Min Act: -0.1700

Data Index: 6668760 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8590. Min Act: -0.1700

Data Index: 4799920 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8454. Min Act: -0.1700

Data Index: 3178209 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8378. Min Act: -0.1700

Data Index: 496734 (Open Web Text)

Max Activating Token Index: 999

Text #4

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8144. Min Act: -0.1700

Data Index: 3915588 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8077. Min Act: -0.1700

Data Index: 7389958 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8107. Min Act: -0.1700

Data Index: 2472999 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8058. Min Act: -0.1700

Data Index: 7447262 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8158. Min Act: -0.1700

Data Index: 6535418 (Open Web Text)

Max Activating Token Index: 1009

Text #9

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8195. Min Act: -0.1700

Data Index: 6000087 (Open Web Text)

Max Activating Token Index: 994

Text #10

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8077. Min Act: -0.1700

Data Index: 3554523 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8118. Min Act: -0.1700

Data Index: 6912535 (Open Web Text)

Max Activating Token Index: 998

Text #12

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7999. Min Act: -0.1700

Data Index: 4503355 (Open Web Text)

Max Activating Token Index: 513

Text #13

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8069. Min Act: -0.1700

Data Index: 1406214 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7882. Min Act: -0.1700

Data Index: 7043254 (Open Web Text)

Max Activating Token Index: 520

Text #15

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7988. Min Act: -0.1700

Data Index: 1515791 (Open Web Text)

Max Activating Token Index: 501

Text #16

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7941. Min Act: -0.1700

Data Index: 614372 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7889. Min Act: -0.1700

Data Index: 239349 (Open Web Text)

Max Activating Token Index: 1001

Text #18

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.8001. Min Act: -0.1700

Data Index: 6845944 (Open Web Text)

Max Activating Token Index: 1010

Text #19

Max Range: 0.8685. Min Range: -0.8685

Max Act: 0.7936. Min Act: -0.1700

Data Index: 4807768 (Open Web Text)

Max Activating Token Index: 527