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

Dataset: Open Web Text

Neuron 1992 in Layer 3

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: 3.7345. Min Range: -3.7345

Max Act: 3.7345. Min Act: -0.1700

Data Index: 206923 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.6365. Min Act: -0.1700

Data Index: 668808 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.6037. Min Act: -0.1700

Data Index: 1875626 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5701. Min Act: -0.1700

Data Index: 2185872 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.6113. Min Act: -0.1700

Data Index: 3842830 (Open Web Text)

Max Activating Token Index: 1011

Text #5

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5944. Min Act: -0.1700

Data Index: 7695157 (Open Web Text)

Max Activating Token Index: 808

Text #6

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.6032. Min Act: -0.1700

Data Index: 8055755 (Open Web Text)

Max Activating Token Index: 858

Text #7

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5698. Min Act: -0.1700

Data Index: 4387926 (Open Web Text)

Max Activating Token Index: 788

Text #8

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5711. Min Act: -0.1700

Data Index: 4835068 (Open Web Text)

Max Activating Token Index: 114

Text #9

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5521. Min Act: -0.1700

Data Index: 1655340 (Open Web Text)

Max Activating Token Index: 922

Text #10

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5721. Min Act: -0.1700

Data Index: 8700838 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5535. Min Act: -0.1700

Data Index: 1715283 (Open Web Text)

Max Activating Token Index: 234

Text #12

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5644. Min Act: -0.1700

Data Index: 5757789 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5450. Min Act: -0.1700

Data Index: 8418500 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5796. Min Act: -0.1700

Data Index: 8067165 (Open Web Text)

Max Activating Token Index: 92

Text #15

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5480. Min Act: -0.1700

Data Index: 2267482 (Open Web Text)

Max Activating Token Index: 925

Text #16

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5791. Min Act: -0.1700

Data Index: 7489752 (Open Web Text)

Max Activating Token Index: 92

Text #17

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5257. Min Act: -0.1700

Data Index: 647919 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5830. Min Act: -0.1700

Data Index: 1247090 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 3.7345. Min Range: -3.7345

Max Act: 3.5417. Min Act: -0.1700

Data Index: 5164743 (Open Web Text)

Max Activating Token Index: 390