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

Dataset: Open Web Text

Neuron 2959 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: 4.0165. Min Range: -4.0165

Max Act: 4.0165. Min Act: -0.1700

Data Index: 8478515 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 4.0165. Min Range: -4.0165

Max Act: 4.0056. Min Act: -0.1700

Data Index: 4226235 (Open Web Text)

Max Activating Token Index: 54

Text #2

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9977. Min Act: -0.1700

Data Index: 8799745 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 7001248 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 5988801 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 8340631 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9588. Min Act: -0.1700

Data Index: 7686602 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 517098 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 854240 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 5832247 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 7634214 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 4990237 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 6954128 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 4236637 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 1450250 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 3939550 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 6348804 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 3624378 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 398145 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.0165. Min Range: -4.0165

Max Act: 3.9670. Min Act: -0.1700

Data Index: 2976913 (Open Web Text)

Max Activating Token Index: 2