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

Dataset: Open Web Text

Neuron 2308 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: 3.0764. Min Range: -3.0764

Max Act: 3.0764. Min Act: -0.1700

Data Index: 540516 (Open Web Text)

Max Activating Token Index: 292

Text #1

Max Range: 3.0764. Min Range: -3.0764

Max Act: 3.0223. Min Act: -0.1700

Data Index: 7086582 (Open Web Text)

Max Activating Token Index: 503

Text #2

Max Range: 3.0764. Min Range: -3.0764

Max Act: 3.0336. Min Act: -0.1700

Data Index: 8084939 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 3.0764. Min Range: -3.0764

Max Act: 3.0114. Min Act: -0.1700

Data Index: 1656923 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.0764. Min Range: -3.0764

Max Act: 3.0136. Min Act: -0.1700

Data Index: 2809882 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 3.0764. Min Range: -3.0764

Max Act: 3.0013. Min Act: -0.1700

Data Index: 4253115 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9786. Min Act: -0.1700

Data Index: 4253114 (Open Web Text)

Max Activating Token Index: 973

Text #7

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9811. Min Act: -0.1700

Data Index: 8015021 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9840. Min Act: -0.1700

Data Index: 8324539 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9853. Min Act: -0.1700

Data Index: 3321600 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9695. Min Act: -0.1700

Data Index: 906266 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9656. Min Act: -0.1700

Data Index: 787915 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9788. Min Act: -0.1700

Data Index: 4224656 (Open Web Text)

Max Activating Token Index: 346

Text #13

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9700. Min Act: -0.1700

Data Index: 7832739 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9976. Min Act: -0.1700

Data Index: 6293822 (Open Web Text)

Max Activating Token Index: 225

Text #15

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9630. Min Act: -0.1700

Data Index: 5929442 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9564. Min Act: -0.1700

Data Index: 5393375 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9643. Min Act: -0.1700

Data Index: 3802471 (Open Web Text)

Max Activating Token Index: 860

Text #18

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9515. Min Act: -0.1700

Data Index: 5943782 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 3.0764. Min Range: -3.0764

Max Act: 2.9650. Min Act: -0.1700

Data Index: 609718 (Open Web Text)

Max Activating Token Index: 290