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

Dataset: Open Web Text

Neuron 2052 in Layer 2

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: 1.8752. Min Range: -1.8752

Max Act: 1.8752. Min Act: -0.1700

Data Index: 1806526 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.8339. Min Act: -0.1700

Data Index: 3533450 (Open Web Text)

Max Activating Token Index: 263

Text #2

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.8259. Min Act: -0.1700

Data Index: 6787769 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7947. Min Act: -0.1700

Data Index: 4718957 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7653. Min Act: -0.1700

Data Index: 1580744 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7768. Min Act: -0.1700

Data Index: 3538927 (Open Web Text)

Max Activating Token Index: 888

Text #6

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7772. Min Act: -0.1700

Data Index: 4751935 (Open Web Text)

Max Activating Token Index: 58

Text #7

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7573. Min Act: -0.1700

Data Index: 3882319 (Open Web Text)

Max Activating Token Index: 748

Text #8

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7518. Min Act: -0.1700

Data Index: 1940143 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7440. Min Act: -0.1700

Data Index: 2274064 (Open Web Text)

Max Activating Token Index: 749

Text #10

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7217. Min Act: -0.1700

Data Index: 2885930 (Open Web Text)

Max Activating Token Index: 194

Text #11

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7093. Min Act: -0.1700

Data Index: 3601341 (Open Web Text)

Max Activating Token Index: 238

Text #12

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7055. Min Act: -0.1700

Data Index: 5957695 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7051. Min Act: -0.1700

Data Index: 3724948 (Open Web Text)

Max Activating Token Index: 718

Text #14

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7053. Min Act: -0.1700

Data Index: 2661783 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.7050. Min Act: -0.1700

Data Index: 6239828 (Open Web Text)

Max Activating Token Index: 142

Text #16

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.6956. Min Act: -0.1700

Data Index: 5928915 (Open Web Text)

Max Activating Token Index: 944

Text #17

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.6840. Min Act: -0.1700

Data Index: 5856581 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.6904. Min Act: -0.1700

Data Index: 1467355 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 1.8752. Min Range: -1.8752

Max Act: 1.6953. Min Act: -0.1700

Data Index: 6542296 (Open Web Text)

Max Activating Token Index: 30