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

Dataset: Open Web Text

Neuron 1161 in Layer 4

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: 2.4636. Min Range: -2.4636

Max Act: 2.4636. Min Act: -0.1700

Data Index: 8263172 (Open Web Text)

Max Activating Token Index: 983

Text #1

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3830. Min Act: -0.1700

Data Index: 850452 (Open Web Text)

Max Activating Token Index: 1000

Text #2

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3846. Min Act: -0.1700

Data Index: 4287887 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3842. Min Act: -0.1700

Data Index: 3960943 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3372. Min Act: -0.1700

Data Index: 2441411 (Open Web Text)

Max Activating Token Index: 994

Text #5

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3190. Min Act: -0.1700

Data Index: 6428238 (Open Web Text)

Max Activating Token Index: 937

Text #6

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3233. Min Act: -0.1700

Data Index: 780500 (Open Web Text)

Max Activating Token Index: 927

Text #7

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3230. Min Act: -0.1700

Data Index: 7747036 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3149. Min Act: -0.1700

Data Index: 6692307 (Open Web Text)

Max Activating Token Index: 968

Text #9

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2880. Min Act: -0.1700

Data Index: 1952897 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3042. Min Act: -0.1700

Data Index: 7022459 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3077. Min Act: -0.1700

Data Index: 3047190 (Open Web Text)

Max Activating Token Index: 973

Text #12

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3130. Min Act: -0.1700

Data Index: 425507 (Open Web Text)

Max Activating Token Index: 959

Text #13

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2821. Min Act: -0.1700

Data Index: 4964939 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2829. Min Act: -0.1700

Data Index: 7522434 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2749. Min Act: -0.1700

Data Index: 3828817 (Open Web Text)

Max Activating Token Index: 993

Text #16

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.3084. Min Act: -0.1700

Data Index: 7184690 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2574. Min Act: -0.1700

Data Index: 2328414 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2558. Min Act: -0.1700

Data Index: 5332600 (Open Web Text)

Max Activating Token Index: 966

Text #19

Max Range: 2.4636. Min Range: -2.4636

Max Act: 2.2622. Min Act: -0.1700

Data Index: 5351444 (Open Web Text)

Max Activating Token Index: 894