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

Dataset: Open Web Text

Neuron 2727 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: 3.7670. Min Range: -3.7670

Max Act: 3.7670. Min Act: -0.1700

Data Index: 7238124 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.7588. Min Act: -0.1700

Data Index: 6975322 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6820. Min Act: -0.1700

Data Index: 4733224 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6764. Min Act: -0.1700

Data Index: 1773612 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6795. Min Act: -0.1700

Data Index: 7064927 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6827. Min Act: -0.1700

Data Index: 6138071 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6854. Min Act: -0.1700

Data Index: 7542001 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6788. Min Act: -0.1700

Data Index: 4847667 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6830. Min Act: -0.1700

Data Index: 2124161 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6623. Min Act: -0.1700

Data Index: 2991228 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6728. Min Act: -0.1700

Data Index: 3053885 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6488. Min Act: -0.1700

Data Index: 5227271 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6728. Min Act: -0.1700

Data Index: 5257936 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6470. Min Act: -0.1700

Data Index: 5815811 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6627. Min Act: -0.1700

Data Index: 3485617 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6728. Min Act: -0.1700

Data Index: 6059903 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6728. Min Act: -0.1700

Data Index: 2906430 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6513. Min Act: -0.1700

Data Index: 558871 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6700. Min Act: -0.1700

Data Index: 6281425 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.7670. Min Range: -3.7670

Max Act: 3.6530. Min Act: -0.1700

Data Index: 4294932 (Open Web Text)

Max Activating Token Index: 4