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

Dataset: Open Web Text

Neuron 161 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: 3.4971. Min Range: -3.4971

Max Act: 3.4971. Min Act: -0.1700

Data Index: 1638733 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.4787. Min Act: -0.1700

Data Index: 6549460 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.4774. Min Act: -0.1700

Data Index: 3666642 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3910. Min Act: -0.1700

Data Index: 2410822 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.4062. Min Act: -0.1700

Data Index: 1106068 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.4023. Min Act: -0.1700

Data Index: 3475154 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3968. Min Act: -0.1700

Data Index: 6622761 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3987. Min Act: -0.1700

Data Index: 6557564 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3792. Min Act: -0.1700

Data Index: 6755882 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3817. Min Act: -0.1700

Data Index: 1524949 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3636. Min Act: -0.1700

Data Index: 4751993 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3780. Min Act: -0.1700

Data Index: 2858774 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3604. Min Act: -0.1700

Data Index: 8668604 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3604. Min Act: -0.1700

Data Index: 1636561 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3604. Min Act: -0.1700

Data Index: 5059668 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3531. Min Act: -0.1700

Data Index: 6685753 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3473. Min Act: -0.1700

Data Index: 7635458 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3302. Min Act: -0.1700

Data Index: 4978278 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3348. Min Act: -0.1700

Data Index: 3092079 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4971. Min Range: -3.4971

Max Act: 3.3084. Min Act: -0.1700

Data Index: 3368963 (Open Web Text)

Max Activating Token Index: 4