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

Dataset: Open Web Text

Neuron 586 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: 3.5833. Min Range: -3.5833

Max Act: 3.5833. Min Act: -0.1700

Data Index: 2988379 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.5545. Min Act: -0.1700

Data Index: 990579 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.5390. Min Act: -0.1700

Data Index: 7516819 (Open Web Text)

Max Activating Token Index: 936

Text #3

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.5116. Min Act: -0.1700

Data Index: 6613845 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.5269. Min Act: -0.1700

Data Index: 1396527 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.5021. Min Act: -0.1700

Data Index: 7534630 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4968. Min Act: -0.1700

Data Index: 5421282 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4964. Min Act: -0.1700

Data Index: 983345 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4971. Min Act: -0.1700

Data Index: 6378780 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4835. Min Act: -0.1700

Data Index: 197042 (Open Web Text)

Max Activating Token Index: 718

Text #10

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4759. Min Act: -0.1700

Data Index: 7835544 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4660. Min Act: -0.1700

Data Index: 2025206 (Open Web Text)

Max Activating Token Index: 1007

Text #12

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4566. Min Act: -0.1700

Data Index: 103067 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4418. Min Act: -0.1700

Data Index: 5766604 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4595. Min Act: -0.1700

Data Index: 3434011 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4443. Min Act: -0.1700

Data Index: 3432749 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4579. Min Act: -0.1700

Data Index: 3406391 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4526. Min Act: -0.1700

Data Index: 6739902 (Open Web Text)

Max Activating Token Index: 395

Text #18

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4566. Min Act: -0.1700

Data Index: 812282 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 3.5833. Min Range: -3.5833

Max Act: 3.4786. Min Act: -0.1700

Data Index: 6846733 (Open Web Text)

Max Activating Token Index: 319