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

Dataset: Open Web Text

Neuron 1069 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: 5.7865. Min Range: -5.7865

Max Act: 5.7865. Min Act: -0.1700

Data Index: 1694141 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.7344. Min Act: -0.1700

Data Index: 1161588 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.7341. Min Act: -0.1700

Data Index: 6956934 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6914. Min Act: -0.1700

Data Index: 7916543 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6642. Min Act: -0.1700

Data Index: 6661031 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6752. Min Act: -0.1700

Data Index: 7647294 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6456. Min Act: -0.1700

Data Index: 2816553 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6160. Min Act: -0.1700

Data Index: 112802 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6266. Min Act: -0.1700

Data Index: 8315522 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6016. Min Act: -0.1700

Data Index: 1368375 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.6087. Min Act: -0.1700

Data Index: 6410226 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5997. Min Act: -0.1700

Data Index: 4830813 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5838. Min Act: -0.1700

Data Index: 5172913 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5627. Min Act: -0.1700

Data Index: 8268524 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5799. Min Act: -0.1700

Data Index: 345389 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5697. Min Act: -0.1700

Data Index: 2362584 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5909. Min Act: -0.1700

Data Index: 3838277 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5838. Min Act: -0.1700

Data Index: 1927109 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5522. Min Act: -0.1700

Data Index: 2449306 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.7865. Min Range: -5.7865

Max Act: 5.5573. Min Act: -0.1700

Data Index: 2591946 (Open Web Text)

Max Activating Token Index: 5