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

Dataset: Open Web Text

Neuron 28 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: 0.8618. Min Range: -0.8618

Max Act: 0.8618. Min Act: -0.1700

Data Index: 6675970 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8367. Min Act: -0.1700

Data Index: 7253638 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8202. Min Act: -0.1700

Data Index: 1487839 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8173. Min Act: -0.1700

Data Index: 2677995 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8110. Min Act: -0.1700

Data Index: 1988199 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8015. Min Act: -0.1700

Data Index: 3894879 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8070. Min Act: -0.1700

Data Index: 6773205 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8027. Min Act: -0.1700

Data Index: 2780463 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8027. Min Act: -0.1700

Data Index: 3068997 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7984. Min Act: -0.1700

Data Index: 6071230 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7948. Min Act: -0.1700

Data Index: 5000242 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7959. Min Act: -0.1700

Data Index: 6773193 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.8010. Min Act: -0.1700

Data Index: 5765116 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7935. Min Act: -0.1700

Data Index: 1350350 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7946. Min Act: -0.1700

Data Index: 6582533 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7878. Min Act: -0.1700

Data Index: 2442109 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7824. Min Act: -0.1700

Data Index: 6626222 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7899. Min Act: -0.1700

Data Index: 4237150 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7890. Min Act: -0.1700

Data Index: 2245786 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 0.8618. Min Range: -0.8618

Max Act: 0.7798. Min Act: -0.1700

Data Index: 4792140 (Open Web Text)

Max Activating Token Index: 6