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

Dataset: Open Web Text

Neuron 954 in Layer 5

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: 5.0856. Min Range: -5.0856

Max Act: 5.0856. Min Act: -0.1700

Data Index: 7126660 (Open Web Text)

Max Activating Token Index: 921

Text #1

Max Range: 5.0856. Min Range: -5.0856

Max Act: 5.0286. Min Act: -0.1700

Data Index: 1759317 (Open Web Text)

Max Activating Token Index: 901

Text #2

Max Range: 5.0856. Min Range: -5.0856

Max Act: 5.0081. Min Act: -0.1700

Data Index: 5873724 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 5.0856. Min Range: -5.0856

Max Act: 5.0136. Min Act: -0.1700

Data Index: 5539185 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 5.0856. Min Range: -5.0856

Max Act: 5.0156. Min Act: -0.1700

Data Index: 3377861 (Open Web Text)

Max Activating Token Index: 174

Text #5

Max Range: 5.0856. Min Range: -5.0856

Max Act: 5.0170. Min Act: -0.1700

Data Index: 7530682 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 5.0856. Min Range: -5.0856

Max Act: 5.0206. Min Act: -0.1700

Data Index: 2585909 (Open Web Text)

Max Activating Token Index: 615

Text #7

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9707. Min Act: -0.1700

Data Index: 1609732 (Open Web Text)

Max Activating Token Index: 971

Text #8

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9794. Min Act: -0.1700

Data Index: 7555867 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9921. Min Act: -0.1700

Data Index: 1687188 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9954. Min Act: -0.1700

Data Index: 2306212 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9432. Min Act: -0.1700

Data Index: 1596310 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9550. Min Act: -0.1700

Data Index: 37438 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9129. Min Act: -0.1700

Data Index: 8367902 (Open Web Text)

Max Activating Token Index: 688

Text #14

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9628. Min Act: -0.1700

Data Index: 7694686 (Open Web Text)

Max Activating Token Index: 798

Text #15

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9500. Min Act: -0.1700

Data Index: 7040225 (Open Web Text)

Max Activating Token Index: 957

Text #16

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9305. Min Act: -0.1700

Data Index: 1943693 (Open Web Text)

Max Activating Token Index: 761

Text #17

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9178. Min Act: -0.1700

Data Index: 268301 (Open Web Text)

Max Activating Token Index: 638

Text #18

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.8859. Min Act: -0.1700

Data Index: 3368023 (Open Web Text)

Max Activating Token Index: 1008

Text #19

Max Range: 5.0856. Min Range: -5.0856

Max Act: 4.9196. Min Act: -0.1700

Data Index: 3811018 (Open Web Text)

Max Activating Token Index: 895