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

Dataset: Open Web Text

Neuron 2836 in Layer 6

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: 4.3955. Min Range: -4.3955

Max Act: 4.3955. Min Act: -0.1700

Data Index: 18879 (Open Web Text)

Max Activating Token Index: 595

Text #1

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3212. Min Act: -0.1700

Data Index: 991464 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3368. Min Act: -0.1700

Data Index: 4043407 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3402. Min Act: -0.1700

Data Index: 1864118 (Open Web Text)

Max Activating Token Index: 598

Text #4

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3307. Min Act: -0.1700

Data Index: 7180310 (Open Web Text)

Max Activating Token Index: 215

Text #5

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3756. Min Act: -0.1700

Data Index: 8046221 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3378. Min Act: -0.1700

Data Index: 2971020 (Open Web Text)

Max Activating Token Index: 559

Text #7

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2986. Min Act: -0.1700

Data Index: 6372810 (Open Web Text)

Max Activating Token Index: 776

Text #8

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2920. Min Act: -0.1700

Data Index: 3938838 (Open Web Text)

Max Activating Token Index: 178

Text #9

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3140. Min Act: -0.1700

Data Index: 8639644 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.3167. Min Act: -0.1700

Data Index: 2428321 (Open Web Text)

Max Activating Token Index: 811

Text #11

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2746. Min Act: -0.1700

Data Index: 5224709 (Open Web Text)

Max Activating Token Index: 495

Text #12

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2710. Min Act: -0.1700

Data Index: 5569243 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2681. Min Act: -0.1700

Data Index: 1834523 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2840. Min Act: -0.1700

Data Index: 8352329 (Open Web Text)

Max Activating Token Index: 191

Text #15

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2828. Min Act: -0.1700

Data Index: 6481175 (Open Web Text)

Max Activating Token Index: 132

Text #16

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2670. Min Act: -0.1700

Data Index: 3499535 (Open Web Text)

Max Activating Token Index: 235

Text #17

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2809. Min Act: -0.1700

Data Index: 3255524 (Open Web Text)

Max Activating Token Index: 346

Text #18

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2522. Min Act: -0.1700

Data Index: 2544800 (Open Web Text)

Max Activating Token Index: 279

Text #19

Max Range: 4.3955. Min Range: -4.3955

Max Act: 4.2293. Min Act: -0.1700

Data Index: 5846256 (Open Web Text)

Max Activating Token Index: 441