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

Dataset: Open Web Text

Neuron 2289 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: 3.2462. Min Range: -3.2462

Max Act: 3.2445. Min Act: -0.1700

Data Index: 5774660 (Open Web Text)

Max Activating Token Index: 549

Text #1

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2356. Min Act: -0.1700

Data Index: 1296890 (Open Web Text)

Max Activating Token Index: 666

Text #2

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2399. Min Act: -0.1700

Data Index: 6167984 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2462. Min Act: -0.1700

Data Index: 6298003 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2013. Min Act: -0.1700

Data Index: 7425082 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2210. Min Act: -0.1700

Data Index: 916484 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2085. Min Act: -0.1700

Data Index: 3722735 (Open Web Text)

Max Activating Token Index: 212

Text #7

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2145. Min Act: -0.1700

Data Index: 815452 (Open Web Text)

Max Activating Token Index: 842

Text #8

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2068. Min Act: -0.1700

Data Index: 4475951 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2076. Min Act: -0.1700

Data Index: 3201241 (Open Web Text)

Max Activating Token Index: 23

Text #10

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2082. Min Act: -0.1700

Data Index: 2962474 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2088. Min Act: -0.1700

Data Index: 1938273 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.1974. Min Act: -0.1700

Data Index: 1635651 (Open Web Text)

Max Activating Token Index: 820

Text #13

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2033. Min Act: -0.1700

Data Index: 6128935 (Open Web Text)

Max Activating Token Index: 144

Text #14

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.2237. Min Act: -0.1700

Data Index: 5191016 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.1726. Min Act: -0.1700

Data Index: 1207703 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.1638. Min Act: -0.1700

Data Index: 3540397 (Open Web Text)

Max Activating Token Index: 735

Text #17

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.1859. Min Act: -0.1700

Data Index: 3614830 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.1689. Min Act: -0.1700

Data Index: 3733842 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 3.2462. Min Range: -3.2462

Max Act: 3.1881. Min Act: -0.1700

Data Index: 3764013 (Open Web Text)

Max Activating Token Index: 95