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

Dataset: Open Web Text

Neuron 2534 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: 3.4256. Min Range: -3.4256

Max Act: 3.4256. Min Act: -0.1700

Data Index: 1284429 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.3225. Min Act: -0.1700

Data Index: 3452446 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.3161. Min Act: -0.1700

Data Index: 6365179 (Open Web Text)

Max Activating Token Index: 718

Text #3

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.3136. Min Act: -0.1700

Data Index: 4016892 (Open Web Text)

Max Activating Token Index: 487

Text #4

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.3144. Min Act: -0.1700

Data Index: 4107674 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2910. Min Act: -0.1700

Data Index: 4358802 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2992. Min Act: -0.1700

Data Index: 4558402 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2870. Min Act: -0.1700

Data Index: 4056849 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2613. Min Act: -0.1700

Data Index: 6152518 (Open Web Text)

Max Activating Token Index: 181

Text #9

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2672. Min Act: -0.1700

Data Index: 3133298 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2689. Min Act: -0.1700

Data Index: 2740036 (Open Web Text)

Max Activating Token Index: 372

Text #11

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2696. Min Act: -0.1700

Data Index: 7369213 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2594. Min Act: -0.1700

Data Index: 4671376 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2715. Min Act: -0.1700

Data Index: 282660 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2612. Min Act: -0.1700

Data Index: 7139616 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2796. Min Act: -0.1700

Data Index: 7055676 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2750. Min Act: -0.1700

Data Index: 3418351 (Open Web Text)

Max Activating Token Index: 177

Text #17

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2517. Min Act: -0.1700

Data Index: 4089304 (Open Web Text)

Max Activating Token Index: 739

Text #18

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2517. Min Act: -0.1700

Data Index: 5386382 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 3.4256. Min Range: -3.4256

Max Act: 3.2581. Min Act: -0.1700

Data Index: 2290686 (Open Web Text)

Max Activating Token Index: 327