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

Dataset: Open Web Text

Neuron 1140 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: 2.9983. Min Range: -2.9983

Max Act: 2.9983. Min Act: -0.1700

Data Index: 7857584 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9930. Min Act: -0.1700

Data Index: 7699402 (Open Web Text)

Max Activating Token Index: 898

Text #2

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9805. Min Act: -0.1700

Data Index: 2452755 (Open Web Text)

Max Activating Token Index: 885

Text #3

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9713. Min Act: -0.1700

Data Index: 460046 (Open Web Text)

Max Activating Token Index: 874

Text #4

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9875. Min Act: -0.1700

Data Index: 4228525 (Open Web Text)

Max Activating Token Index: 942

Text #5

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9746. Min Act: -0.1700

Data Index: 4738640 (Open Web Text)

Max Activating Token Index: 906

Text #6

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9581. Min Act: -0.1700

Data Index: 1857165 (Open Web Text)

Max Activating Token Index: 872

Text #7

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9504. Min Act: -0.1700

Data Index: 4602854 (Open Web Text)

Max Activating Token Index: 875

Text #8

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9489. Min Act: -0.1700

Data Index: 5294742 (Open Web Text)

Max Activating Token Index: 882

Text #9

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9420. Min Act: -0.1700

Data Index: 2161332 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9599. Min Act: -0.1700

Data Index: 1852614 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9455. Min Act: -0.1700

Data Index: 4467636 (Open Web Text)

Max Activating Token Index: 896

Text #12

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9489. Min Act: -0.1700

Data Index: 1565003 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9592. Min Act: -0.1700

Data Index: 8747892 (Open Web Text)

Max Activating Token Index: 883

Text #14

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9465. Min Act: -0.1700

Data Index: 8460396 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9366. Min Act: -0.1700

Data Index: 5007921 (Open Web Text)

Max Activating Token Index: 895

Text #16

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9324. Min Act: -0.1700

Data Index: 1837417 (Open Web Text)

Max Activating Token Index: 1019

Text #17

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9378. Min Act: -0.1700

Data Index: 3580993 (Open Web Text)

Max Activating Token Index: 879

Text #18

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9378. Min Act: -0.1700

Data Index: 439440 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 2.9983. Min Range: -2.9983

Max Act: 2.9283. Min Act: -0.1700

Data Index: 5544911 (Open Web Text)

Max Activating Token Index: 887