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

Dataset: Open Web Text

Neuron 2535 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: 3.2739. Min Range: -3.2739

Max Act: 3.2739. Min Act: -0.1700

Data Index: 513067 (Open Web Text)

Max Activating Token Index: 185

Text #1

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2688. Min Act: -0.1700

Data Index: 500070 (Open Web Text)

Max Activating Token Index: 302

Text #2

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2685. Min Act: -0.1700

Data Index: 7327461 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2445. Min Act: -0.1700

Data Index: 6725635 (Open Web Text)

Max Activating Token Index: 905

Text #4

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2484. Min Act: -0.1700

Data Index: 3398368 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2397. Min Act: -0.1700

Data Index: 4957789 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2235. Min Act: -0.1700

Data Index: 5342027 (Open Web Text)

Max Activating Token Index: 898

Text #7

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2362. Min Act: -0.1700

Data Index: 3773008 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2393. Min Act: -0.1700

Data Index: 8808424 (Open Web Text)

Max Activating Token Index: 915

Text #9

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2320. Min Act: -0.1700

Data Index: 8360128 (Open Web Text)

Max Activating Token Index: 919

Text #10

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2362. Min Act: -0.1700

Data Index: 5197835 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2362. Min Act: -0.1700

Data Index: 5183035 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2209. Min Act: -0.1700

Data Index: 4688330 (Open Web Text)

Max Activating Token Index: 851

Text #13

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2272. Min Act: -0.1700

Data Index: 7208205 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2113. Min Act: -0.1700

Data Index: 2142898 (Open Web Text)

Max Activating Token Index: 755

Text #15

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.1954. Min Act: -0.1700

Data Index: 2417943 (Open Web Text)

Max Activating Token Index: 545

Text #16

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2023. Min Act: -0.1700

Data Index: 3364765 (Open Web Text)

Max Activating Token Index: 29

Text #17

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2089. Min Act: -0.1700

Data Index: 288802 (Open Web Text)

Max Activating Token Index: 27

Text #18

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2037. Min Act: -0.1700

Data Index: 3931435 (Open Web Text)

Max Activating Token Index: 1015

Text #19

Max Range: 3.2739. Min Range: -3.2739

Max Act: 3.2125. Min Act: -0.1700

Data Index: 6432390 (Open Web Text)

Max Activating Token Index: 34