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

Dataset: Open Web Text

Neuron 136 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: 3.7829. Min Range: -3.7829

Max Act: 3.7829. Min Act: -0.1700

Data Index: 91438 (Open Web Text)

Max Activating Token Index: 978

Text #1

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.7376. Min Act: -0.1700

Data Index: 7589841 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6308. Min Act: -0.1700

Data Index: 5820935 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6550. Min Act: -0.1700

Data Index: 5254724 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6176. Min Act: -0.1700

Data Index: 7349688 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6175. Min Act: -0.1700

Data Index: 8111413 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5983. Min Act: -0.1700

Data Index: 6633790 (Open Web Text)

Max Activating Token Index: 941

Text #7

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5875. Min Act: -0.1700

Data Index: 6608979 (Open Web Text)

Max Activating Token Index: 845

Text #8

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6112. Min Act: -0.1700

Data Index: 7961669 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6059. Min Act: -0.1700

Data Index: 2247249 (Open Web Text)

Max Activating Token Index: 95

Text #10

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5910. Min Act: -0.1700

Data Index: 2386627 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.6281. Min Act: -0.1700

Data Index: 847652 (Open Web Text)

Max Activating Token Index: 980

Text #12

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5873. Min Act: -0.1700

Data Index: 7298376 (Open Web Text)

Max Activating Token Index: 216

Text #13

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5654. Min Act: -0.1700

Data Index: 2737476 (Open Web Text)

Max Activating Token Index: 378

Text #14

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5917. Min Act: -0.1700

Data Index: 7180540 (Open Web Text)

Max Activating Token Index: 313

Text #15

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5834. Min Act: -0.1700

Data Index: 2122470 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5698. Min Act: -0.1700

Data Index: 6313817 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5762. Min Act: -0.1700

Data Index: 6285961 (Open Web Text)

Max Activating Token Index: 111

Text #18

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5481. Min Act: -0.1700

Data Index: 295114 (Open Web Text)

Max Activating Token Index: 970

Text #19

Max Range: 3.7829. Min Range: -3.7829

Max Act: 3.5749. Min Act: -0.1700

Data Index: 6761138 (Open Web Text)

Max Activating Token Index: 79